Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 7645. Отображено 100.
22-03-2012 дата публикации

Image processing based on visual attention and reduced search based generated regions of interest

Номер: US20120070075A1
Автор: Lalitha M. Eswara
Принадлежит: Honeywell International Inc

A system for complexity reduction in images involving concepts of visual attention based most probable region detection for object presence and perspective-view based reduced scale-search approaches. Visual attention concept in context uses gradient and contrast of an image. A pixel meeting certain criteria for gradient or contrast values may be further processed for object presence. Limiting image processing to such regions may reduce the complexity of digitized images. Post processing the outcome using morphological operations like dilation and erosion appropriately may help retain some of the missed object pixels in the resultant image. Typically image blocks at different scales are searched for object presence. Reduced-scale search involves removing certain scales during search. As object size in image varies with its location scales within a given scale-range if searched, may lead to higher chances of object presence. This is implemented using relative heights and widths estimation using the perspective view concept.

Подробнее
Номер записи: 1
14-03-2013 дата публикации

Methods and Apparatus for Image Analysis and Modification Using Fast Sliding Parabola Erosian

Номер: US20130064468A1
Автор: Kaupo Palo, Peet Kask
Принадлежит: PerkinElmer Cellular Technologies Germany GmbH

Methods and apparatus are provided for image analysis and modification using a fast sliding parabola erosion. The methods include selecting a scan line in an image and performing a unidirectional left-hand pass followed by a unidirectional right-hand pass. The unidirectional passes are performed as loops with increasing distance. By utilizing simple unidirectional left-hand and right-hand passes along a scan line in an image, the erosion procedure is greatly simplified and computation times are significantly reduced.

Подробнее
Номер записи: 2
23-01-2014 дата публикации

Apparatus and method for filling hole area of image

Номер: US20140023289A1
Автор: Kee Chang Lee, Seung Won Jung
Принадлежит: SAMSUNG ELECTRONICS CO LTD

Provided is an image processing apparatus and method for filling a hole area in an image. The image processing apparatus may include a candidate pixel setting unit to set a plurality of candidate pixels corresponding to at least one hole pixel in a hole area using neighboring pixels around the hole area, and a pixel value determining unit to determine a pixel value of the hole pixel using the plurality of candidate pixels.

Подробнее
Номер записи: 3
04-01-2018 дата публикации

METHODS AND SYSTEMS FOR EXTRACTING BLOOD VESSEL

Номер: US20180000441A1
Автор: LV Chuanfeng, MAO Yufei, Wang Ce, Wang Xiaodong, WANG Xu, WU Ke, YU Wenjun, ZHAO Peng
Принадлежит: SHANGHAI UNITED IMAGING HEALTHCARE CO., LTD.

A method for extracting a blood vessel may include acquiring an image relating to a blood vessel, the image including multiple slices; determining a region of interest in the image; establishing a blood vessel model; and extracting the blood vessel from the region of interest based on the blood vessel model. 1. A method for extracting a blood vessel implemented on at least one machine each of which has at least one processor and storage , the method comprising:acquiring an image relating to a blood vessel, the image including multiple slices;determining a region of interest in the image;establishing a blood vessel model; andextracting the blood vessel from the region of interest based on the blood vessel model.2. The method of claim 1 , wherein the determining a region of interest in the image comprises:identifying slice information relating to the multiple slices of the image;determining a slice range of the multiple slices corresponding to a sub-image based on the slice information;determining the sub-image in the slice range;acquiring a template based on the sub-image;registering the sub-image based on the template to determine a registered result;identifying the region of interest based on the registered result.3. The method of claim 1 , wherein the determining a region of interest in the image comprises performing machine learning.4. The method of claim 1 , further comprising determining a seed point of the blood vessel including:performing an enhancement operation on the image to obtain an enhanced image;determining gradients of grey values relating to the image to obtain a gradient image;constructing a feature function of the blood vessel based on the enhanced image and the gradient image; anddetermining the seed point of the blood vessel based on the feature function of the blood vessel.5. The method of claim 1 , further comprising determining a centerline of the blood vessel.6. The method of claim 5 , wherein the determining a centerline of the blood vessel ...

Подробнее
Номер записи: 4
04-01-2018 дата публикации

FEATURE CHARACTERIZATION FROM INFRARED RADIATION

Номер: US20180004355A1
Автор: Davies Robert L., Lee Chia-Hsun, Orsten Sterling, Shahar Amit
Принадлежит:

Systems, apparatuses, and/or methods to characterize a user feature. For example, and apparatus may include a pattern receiver to receive a feature infrared (IR) pattern corresponding to non-uniform IR radiation reflected by skin of the user feature and an object IR pattern corresponding to IR radiation reflected by an object. The apparatus may further include a filter to generate a modified IR pattern from the object IR pattern and to remove at least a part of the modified IR pattern from feature IR pattern. In addition, the apparatus may include a feature characterizer to characterize the user feature based on the feature IR pattern. In one example, a computing platform may be controlled based on the characterization of the user feature. 1. A system comprising: an emitter to emit uniform infrared (IR) radiation that is to be converted to non-uniform IR radiation having an IR pattern, and', 'a capturer to capture reflected non-uniform IR radiation,, 'an image device including,'}a pattern receiver to receive a feature IR pattern corresponding to non-uniform IR radiation reflected by skin of a user feature and an object IR pattern corresponding to non-uniform IR radiation reflected by an object,a filter to generate a modified IR pattern from the object IR pattern and to remove at least a part of the modified IR pattern from feature IR pattern, anda feature characterizer to characterize the user feature based on the feature IR pattern.2. The system of claim 1 , further including one or more of claim 1 ,a touch determiner to determine a touch event involving the user feature based on a shadow concentration between the feature IR pattern and the object IR pattern,a proximity determiner to determine proximity of the user feature to the object based on the shadow concentration,a pressure determiner to determine pressure corresponding to a press event involving the user feature based on a pattern change associated with the feature IR pattern, ora depth determiner to ...

Подробнее
Номер записи: 5
07-01-2021 дата публикации

METHOD FOR LOCALIZATION OF BONE MARROW WHITE BLOOD CELLS BASED ON SATURATION CLUSTERING

Номер: US20210004640A1
Автор: Fang Fengqi, HU Jiajia, HUANG Zhen, Li Qiang, Li Shun, Liu Yongtao, Lu Ju
Принадлежит:

A saturation clustering-based method for positioning bone marrow white blood cells: first, pre-processing a bone marrow white blood cell image to eliminate partial noise points and simultaneously smooth the image; using K-means clustering to cluster saturation channels of the bone marrow white blood cell image, and select the type of the white blood cells according to a decision tree algorithm; next, eliminating irrelevant areas in a binary image of the white blood cells by means of a morphology processing algorithm, and simultaneously filling in point holes in the white blood cells; and finally, positioning the white blood cells. The present method is simple and effective, and is suitable for a wide range of applications compared to existing threshold-based algorithms, while rendering a final result more accurate by integrating the decision tree algorithm. 1. A method for locating bone marrow white blood cells , comprising the steps of:(1) median filtering a bone marrow white blood cell image to remove some noise;(2) color-converting the median-filtered bone marrow white blood cell image from an RGB (red, green and blue) channel to an HSV (color, saturation, brightness) channel;(3) applying a K-means algorithm to an S-saturation channel, dividing the color-converted image into three parts, and selecting a first part or a first part and a second part to obtain a white blood cell area;(4) calculating average values (H1, H2) of an H channel in the first part and the second part obtained in step (3), and calculating the area ratio of the first part and the second part according to mean points (S1, S2) of the first part and the second part;(5) performing a statistical analysis on multiple images to identify first parts and second parts where white blood cells are included, and recording the values of H1−H2, S1−S2, and area ratios of the identified first parts and the second parts;(6) according to the recorded results in step (5), applying a decision tree algorithm to ...

Подробнее
Номер записи: 6
02-01-2020 дата публикации

IMAGE PROCESSING METHOD AND IMAGE PROCESSING APPARATUS FOR EXECUTING IMAGE PROCESSING METHOD

Номер: US20200005437A1
Автор: Murase Hiroshi
Принадлежит:

An image processing method includes capturing a display image of a display panel in-focus with a camera; generating a first image by applying a high-pass filter to the captured image to remove or reduce a spatial frequency component corresponding to moiré that has appeared in the captured image; capturing the display image out-of-focus with the camera; generating a second image by applying a correction filter to the captured image to correct attenuation of the spatial frequency component of the captured image with the correction filter, and applying a low-pass filter to the corrected captured image; and generating a third image in which the moiré has been removed or reduced by compositing the first image and the second image. The sum of the transmittance of the high-pass filter and the transmittance of the low-pass filter is a constant value at any spatial frequency. 1. An image processing method in which a display image of a display panel in which pixels are aligned periodically is captured with a camera in which imaging pixels are aligned periodically , and the captured image of the camera is processed , the image processing method comprising:an in-focus image capturing step of capturing the display image in-focus with the camera to obtain a first captured image;a first image generation step of generating a first image by applying a high-pass filter to the first captured image and removing or reducing a spatial frequency component corresponding to moiré that appears in the first captured image;an out-of-focus image capturing step of capturing the display image out-of-focus with the camera to obtain a second captured image;a captured image correction step of correcting attenuation of the spatial frequency component of the second captured image using a correction filter by applying the correction filter to the second captured image;a second image generation step of generating a second image by applying a low-pass filter to the second captured image, the second ...

Подробнее
Номер записи: 7
02-01-2020 дата публикации

Image Component Detection

Номер: US20200007817A1
Автор: Diggins Jonathan
Принадлежит:

A processor unit configured to identify blocks of a frame of a video sequence to be excluded from a motion-compensated operation, the processor unit comprising: a frame processor configured to process pixel values of a first frame to characterise blocks of one or more pixels of the first frame as representing at least a portion of a graphic object; a frame-difference processor configured to determine difference values between blocks of the first frame and corresponding blocks of a second frame, and to process said difference values to characterise blocks of the first frame as representing an image component that is static between the first and second frames; a block identifier configured to identify blocks of the first frame as protected blocks in dependence on blocks characterised as: (i) representing at least a portion of a graphic object; and (ii) representing an image component that is static between the first and second frames, wherein the identified protected blocks are to be excluded from the motion compensated operation. 1. A processor unit configured to identify blocks of a frame of a video sequence to be excluded from a motion-compensated operation , the processor unit comprising:a frame processor configured to process pixel values of a first frame to characterise blocks of one or more pixels of the first frame as representing at least a portion of a graphic object;a frame-difference processor configured to determine difference values between blocks of the first frame and corresponding blocks of a second frame, and to process said difference values to characterise blocks of the first frame as representing an image component that is static between the first and second frames;a block identifier configured to identify blocks of the first frame as protected blocks in dependence on blocks characterised as: (i) representing at least a portion of a graphic object; and (ii) representing an image component that is static between the first and second frames, wherein ...

Подробнее
Номер записи: 8
14-01-2021 дата публикации

Key Point Detection Method and Apparatus, and Storage Medium

Номер: US20210012143A1
Автор: BAO Hujun, LIU Yuan, Peng Sida, Zhou Xiaowei
Принадлежит: ZHEJIANG SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD.

The present disclosure relates to a key point detection method and apparatus, an electronic device and a storage medium. The method comprises: determining an area in which a plurality of pixels of an image to be processed are located and first direction vectors of the plurality of pixels pointing to a key point of the area; and determining the position of the key point in the area based on the area in which the pixels are located and the first direction vectors of the plurality of pixels in the area. 1. A key point detection method , comprising:determining an area in which a plurality of pixels of an image to be processed are located and first direction vectors of the plurality of pixels pointing to a key point of the area, wherein the image to be processed comprises one or more areas; anddetermining the position of the key point in the area based on the area in which the pixels are located and the first direction vectors of the plurality of pixels in the area.2. The method according to claim 1 , wherein the determining the position of the key point in the area based on the area in which the pixels are located and the first direction vectors of the plurality of pixels in the area comprises:determining estimated coordinates of the key point in a target area and weights of the estimated coordinates of the key point based on the area in which the pixels are located and the first direction vectors, wherein the target area is any one of the one or more areas; andperforming weighted averaging on the estimated coordinates of the key point in the target area based on the weights of the estimated coordinates of the key point, to obtain the position of the key point in the target area.3. The method according to claim 2 , wherein the determining the estimated coordinates of the key point in the target area and the weights of the estimated coordinates of the key point based on the area in which the pixels are located and the first direction vectors comprises:screening the ...

Подробнее
Номер записи: 9
21-01-2016 дата публикации

Medical image processing apparatus

Номер: US20160015279A1
Автор: Satoru Ohishi
Принадлежит: Toshiba Corp, Toshiba Medical Systems Corp

According to one embodiment, a medical image processing apparatus includes an acquiring unit, an identifying unit, and a display controller. The acquiring unit acquires volume data indicating the state of a three-dimensional region including a mass portion and a plurality of blood vessels derived from the mass portion in a subject. The identifying unit specifies a region corresponding to the mass portion and the blood vessels in the volume data as a region of interest. The identifying unit identifies the mass portion and each of the blood vessels in the region of interest. The display controller assigns a different display mode to at least one of the mass portion and the blood vessels.

Подробнее
Номер записи: 10
21-01-2016 дата публикации

REGION EXTRACTION APPARATUS, METHOD, AND PROGRAM

Номер: US20160019694A1
Автор: IHARA Satoshi
Принадлежит: FUJIFILM Corporation

An apparatus includes a gaseous region extraction unit that extracts a gaseous region from a lumen image, a residue candidate region extraction unit that extracts a candidate of a residue region from the lumen image as a residue candidate region, a boundary candidate region detection unit that detects a boundary candidate region that includes a boundary between the gaseous region and the residue candidate region, a representative direction component obtaining unit that obtains a representative direction component representing a plurality of directional components of an image in the boundary candidate region, a boundary region detection unit that detects a boundary region that includes a boundary between the gaseous region and the residue region from the boundary candidate regions based on the representative direction component, and a residue region extraction unit that extracts the residue candidate region that includes the boundary region as the residue region.

Подробнее
Номер записи: 11
17-01-2019 дата публикации

METHODS OF YIELD ASSESSMENT WITH CROP PHOTOMETRY

Номер: US20190019281A1
Автор: BERGHOEFER CHAD CLIFFORD, HANSELMAN TRAVIS ALLEN, Hausmann Neil J., MESSINA CARLOS
Принадлежит: PIONEER HI-BRED INTERNATIONAL, INC.

A method of evaluating one or more kernels of an ear of maize using digital imagery that includes acquiring a digital image of the one or more kernels of the ear of maize without the use of spatial reference points, processing the digital image to estimate at least one physical property of the one or more kernels of the ear of maize from the digital image, and evaluating the at least one kernel of maize using the estimate of the at least one physical property of the at least one kernel of maize. The method includes using one or more such digital images to estimate yield on a plant, management zone, field, county and country level. 1. A method of predicting yield of a corn crop , comprising:Obtaining one or more images of an ear of corn without the use of spatial reference points,Determining the number of kernels per ear, andCalculating total yield based on the image.2. The method of claim 1 , wherein an image of the corn ear is positioned within a target window on the viewing screen of an imaging device.3. The method of claim 2 , wherein the one or more images are still images from a video feed of the corn ear.4. The method of claim 2 , wherein the images are selected based on having a corn ear to target window surface area ratio between 70% to 90%.5. The method of claim 4 , wherein the corn kernels on the corn ear are segmented and counted.6. The method of claim 1 , wherein the number of kernels/ear is the median number of kernels from a set of still images.7. The method of claim 6 , wherein the image is a two dimensional image and the total number of kernels/ear is obtained by multiplying the number of kernels visible in the image by a calibration factor within the range of 2.25 to 2.50.8. The method of claim 1 , wherein total yield is calculated based on an estimate of the ears/acre claim 1 , which ears/acre estimate is based on the predicted test weight claim 1 , yield or number of ears per plant of the variety based on one or more of variety differences claim 1 ...

Подробнее
Номер записи: 12
18-01-2018 дата публикации

Image processing apparatus, method, and storage medium

Номер: US20180020118A1
Автор: Koya Shimamura, Reiji Misawa
Принадлежит: Canon Inc

A binary image of an input image is generated, and a character region within the binary image and a region surrounding each character are acquired as character segmentation rectangle information. A thinning process is executed on a region within the binary image which is identified based on the character segmentation rectangle information to acquire a thinned image. An edge detected image of the region identified based on the character segmentation rectangle information is acquired. Whether each character identified based on the character segmentation rectangle information is a character to be separated from a background by the binarization process or not is determined based on a result of a logical AND of the thinned image and the edge detected image.

Подробнее
Номер записи: 13
28-01-2021 дата публикации

HEMODYNAMIC PARAMETER ESTIMATION BASED ON IMAGE DATA

Номер: US20210022617A1
Автор: Nie Yingbin, Zhang Chen, Zhao Zhoushe
Принадлежит:

The present approach relates to determining a reference value based on image data that includes a non-occluded vascular region (such as the ascending aorta in a cardiovascular context). This reference value is compared on a pixel-by pixel basis with the CT values observed in the other vasculature regions. With this in mind, and in a cardiovascular context, the determined FFR value for each pixel is the ratio of CT value in the vascular region of interest to the reference CT value. 1. A method for estimating hemodynamic parameters , comprising the steps of:acquiring vasculature image data using an imaging system;segmenting the vasculature image data into a reference vessel region and into a vessel region of interest;determining a reference value based on the reference vessel region;determining for each pixel of the vessel region of interest a fractional flow reserve (FFR) pixel value based at least in part on a ratio of the original pixel value to the reference value; andgenerating and displaying a FFR image based at least in part on the FFR pixel values determined for the respective pixels of the vessel region of interest.2. The method of claim 1 , wherein the vasculature image data comprises cardiac image data.3. The method of claim 1 , wherein the imaging system comprises a computed tomography (CT) imaging system or a magnetic resonance (MR) imaging system.4. The method of claim 1 , wherein segmenting the vasculature image data comprises:providing the vascular image data as an input to a neural network trained to perform a binary segmentation of the vasculature image data with respect to the reference vessel region and the vessel region of interest.5. The method of claim 1 , wherein the reference vessel region comprises an aortic region and the vessel region of interest comprises a coronary artery region.6. The method of claim 5 , wherein the coronary artery region is further segmented into a left anterior descending artery claim 5 , a right coronary artery claim ...

Подробнее
Номер записи: 14
28-01-2016 дата публикации

LOW MEMORY CONTENT AWARE IMAGE MODIFICATION

Номер: US20160027159A1
Автор: Amirghodsi Sohrab, Darabi Soheil
Принадлежит: ADOBE SYSTEMS INCORPORATED

Techniques are disclosed for generating a modified image. A source image at an original, or high, resolution is downsampled to a lower resolution. One or more mappings between different patches, or regions, of pixels within the source image or across several images are generated from the downsampled image using a patch-based sampling algorithm. Such patch-based sampling algorithms may be used find correspondences between patches of one or more images by defining a nearest-neighbor field as a function of offsets for some distance function of the patches. The mapping is then upsampled to a higher resolution for coherent regions and used to identify fill content in the source image for filling patches in other portions of the image or other images. The fill content is derived from regions of the source image corresponding to the coordinates of the source patch in the upsampled mapping. 1. A computer-implemented method comprising:receiving, by a processor, a source image at an original resolution;generating, using a patch-based sampling algorithm, a mapping between a source patch of pixels in a downsampled version of the source image and a target patch of pixels in the downsampled version of the source image, the downsampled version of the source image having a resolution coarser than the original resolution;upsampling the mapping to a resolution finer than the resolution of the downsampled version of the source image;identifying fill content in a region of the original resolution source image corresponding to coordinates of the source patch of pixels in the upsampled mapping; andplacing the fill content into a target image.2. The method of claim 1 , wherein the source patch of pixels represents a coherent region of a finer resolution version of the source image reconstructed from the downsampled version of the source image.3. The method of claim 1 , further comprising combining the source image and the target image to produce an output image.4. The method of claim 1 , ...

Подробнее
Номер записи: 15
10-02-2022 дата публикации

SYSTEMS AND METHODS FOR SEGMENTING IMAGES

Номер: US20220044413A1
Автор: DE WINDE Lio
Принадлежит:

Embodiments disclosed herein relate to systems and methods for segmenting 2D images. Certain embodiments provide a method of segmenting a 2D image. The method includes obtaining a 2D mask for the 2D image, wherein the 2D mask comprises a portion of the 2D image. The method includes selecting one or more first voxels of the 2D image not part of the 2D mask and adding the one or more first voxels of the 2D image to the 2D mask. The method includes selecting one or more second voxels of the 2D image and performing a morphological closing on one or more third voxels comprising the one or more second voxels of the 2D image that are part of the 2D mask. The method includes performing an automatic flood-fill operation on at least a portion of the 2D mask. 1. A method for using a cursor to perform different operations on different data , comprising:selecting first pixels and second pixels of in image using a cursor comprising a first region and a second region, respectively;performing a first operation on data corresponding to the first pixels; andperforming a second operation, different than the first operation, on data corresponding to the second pixels.2. The method of claim 1 , wherein the first region corresponds to a portion of the second region.3. The method of claim 1 , wherein the first region is one of a circle claim 1 , rectangle and square.4. The method of claim 1 , wherein the second region is one of a circle claim 1 , rectangle and square.5. The method of claim 1 , wherein the first and second regions have a same shape.6. The method of claim 1 , wherein the first and second regions have a different shape.7. The method of claim 1 , wherein selecting the first and second pixels comprises one or more of clicking claim 1 , holding claim 1 , or dragging the cursor over the image.8. The method of claim 1 , wherein the image is one of a plurality of 2D images forming a stack claim 1 , the plurality of 2D images corresponding to a 3D representation of an object.9. The ...

Подробнее
Номер записи: 16
17-02-2022 дата публикации

DERMAL IMAGE CAPTURE

Номер: US20220047165A1
Автор: Chikkanaravangala Shadakshari D., Daley Stephen C., Kurniawan Helmi, Lai Chee Keen, Leong Hon Kuen, Lou Yaolong, Ng Bryan, Perkins David G.
Принадлежит:

A dermal imaging system coordinates operation of an illumination unit, one or more lenses, and a camera to capture a sequence of images of an area of interest on a skin surface. The system automatically tags each image in the sequence of images. The tag for each image identifies a light source, an illumination angle, and a filter selected for capturing the image. The system automatically selects at least one image from the sequence of images, and analyzes the selected image from the sequence of images to provide a recommended skin disease diagnosis. 1. A dermal imaging system , comprising:{'claim-text': ['coordinate operation of the illumination unit, the one or more lenses, and the camera to capture a sequence of images of an area of interest on a skin surface;', 'automatically tag each image in the sequence of images, the tag for each image identifying a light source and illumination angle selected from the illumination unit for capturing the image, and further identifying a filter selected for capturing the image;', 'automatically select at least one image from the sequence of images; and', 'analyze the selected image from the sequence of images to provide a recommended skin disease diagnosis.'], '#text': 'a controller configured to control the operation of a camera, an illumination unit, and one or more lenses, the controller having at least one processor, and a memory storing instructions which, when executed by the at least one processor, cause the system to:'}2. The system of claim 1 , further comprising:the illumination unit, and wherein the illumination unit includes an array of light sources, each light source configured to emit light at a predetermined wavelength.3. The system of claim 2 , wherein the array of light sources are light-emitting diodes claim 2 , lasers claim 2 , or optical lamps.4. The system of claim 1 , wherein the memory stores further instructions which claim 1 , when executed by the at least one processor claim 1 , cause the system to: ...

Подробнее
Номер записи: 17
04-02-2016 дата публикации

METHOD AND SYSTEM FOR COMPUTING DIGITAL TOMOSYNTHESIS IMAGES

Номер: US20160035102A1
Автор: JEREBKO Anna
Принадлежит:

A method of performing digital tomosynthesis includes the steps of obtaining an initial volume (I) formed with a plurality of slices (); performing edge detection in a slice (); processing the detected edges () to obtain a weighting volume (W); and generating a composite slab (S, S) on the basis of the weighting volume (W). 1. A method of performing digital tomosynthesis , which method comprises the steps of{'b': '100', 'obtaining an initial volume (I) comprising a plurality of slices ();'}{'b': '100', 'performing edge detection in a slice ();'}{'b': '11', 'sub': E', 'xyz, 'processing the detected edges () to obtain a weighting volume (W); and'}{'sub': comp', 'meta', 'xyz, 'generating a composite slab (S, S) on the basis of the weighting volume (W).'}2111111. The method according to claim 1 , wherein the step of processing the detected edges () comprises performing morphological dilation on a detected edge () to obtain a dilated edge ().31111. The method according to claim 2 , wherein the step of processing the detected edges () comprises a step of adjusting the transparency in a region of a dilated edge ().411. The method according to claim 3 , which comprises adjusting the transparency in a border region of a dilated edge ().51111. The method according to claim 4 , which comprises gradually increasing the transparency from a central region of the dilated edge () to an outer border of the dilated edge ().61111. The method according to claim 3 , which comprises gradually increasing the transparency from a central region of the dilated edge () to an outer border of the dilated edge ().711. The method according to claim 3 , which comprises applying a Gaussian blur algorithm in the step of adjusting the transparency of the dilated edge ().811. The method according to claim 2 , which comprises adjusting the transparency in a border region of a dilated edge ().9. The method according to claim 1 , comprising a step of generating an AIP slab (S) from a volume (I) for use ...

Подробнее
Номер записи: 18
01-02-2018 дата публикации

METHODS AND SYSTEMS OF PERFORMING ADAPTIVE MORPHOLOGY OPERATIONS IN VIDEO ANALYTICS

Номер: US20180033152A1
Автор: Bi Ning, Chen Ying, Gao Jinglun, Wang Lei
Принадлежит:

Techniques and systems are provided for processing video data. For example, techniques and systems are provided for performing content-adaptive morphology operations. A first erosion function can be performed on a foreground mask of a video frame, including setting one or more foreground pixels of the frame to one or more background pixels. A temporary foreground mask can be generated based on the first erosion function being performed on the foreground mask. One or more connected components can be generated for the frame by performing connected component analysis to connect one or more neighboring foreground pixels. A complexity of the frame (or of the foreground mask of the frame) can be determined by comparing a number of the one or more connected components to a threshold number. A second erosion function can be performed on the temporary foreground mask when the number of the one or more connected components is higher than the threshold number. The one or more connected components can be output for blob processing when the number of the one or more connected components is lower than the threshold number. 1. A method of performing content-adaptive morphology operations , the method comprising:performing a first erosion function on a foreground mask of a frame, the first erosion function setting one or more foreground pixels of the foreground mask to one or more background pixels;determining a complexity of the foreground mask; anddetermining whether to perform one or more additional erosion functions for the frame based on the determined complexity of the foreground mask.2. The method of claim 1 , further comprising:generating one or more connected components by performing connected component analysis on foreground pixels of the foreground mask to connect one or more neighboring foreground pixels; andwherein the complexity of the foreground mask is determined by comparing a number of the one or more connected components to a threshold number.3. The method of ...

Подробнее
Номер записи: 19
09-02-2017 дата публикации

Detection of Borders of Benign and Malignant Lesions Including Melanoma and Basal Cell Carcinoma Using a Geodesic Active Contour (GAC) Technique

Номер: US20170039704A1
Автор: Kasmi Reda
Принадлежит:

A method for automatic segmentation of dermoscopy skin lesion images includes automating a Geodesic Active Contour (GAC) initialization to be sufficiently large to encompass the lesion yet lie near the actual lesion contour. In addition, a new image plane is found by transforming the original RGB image to a smoothed image that allows the GAC to move without sticking on the minimum local energy. This method can eliminate the need for separate hair or noise removal algorithms. The method may include extraction of designated color planes to improve the initial contour and to automatically correct false segmentations. The method includes an algorithm to correct false protuberances and/or false inlets that may be present in the GAC border. A method is given to increase likelihood of including more actual lesion area. The method yields multiple border choices which may be presented to a classifier for optimal border selection. 1. A lesion segmentation method performed on a computer system that automatically finds a border of a lesion shown in a digital image based on a gray scale image comprising a gray scale version of the digital image and on a Red-Green-Blue (RGB) color image comprising an RGB component color version of the digital image , the method comprising:smoothing the gray scale image by convolving the grayscale image with a first spatial filter to generate a smoothed gray scale image;extracting each pixel value of a blue component plane of the RGB color image from each corresponding pixel value of a red component plane of the RGB color image to generate an extracted image;extracting each pixel value of the smoothed grayscale image from each corresponding pixel value of the extracted image to generate a new image;smoothing the new image by convolving the new image with a second spatial filter to generate a smoothed new image;binarizing the smoothed new image to generate a black and white image; andconstructing the border of the lesion as a contour of a pixel ...

Подробнее
Номер записи: 20
07-02-2019 дата публикации

REGION-BASED MOTION ESTIMATION AND MODELING FOR ACCURATE REGION-BASED MOTION COMPENSATION FOR EFFICIENT VIDEO PROCESSING OR CODING

Номер: US20190045193A1
Автор: Puri Atul, Socek Daniel
Принадлежит:

Methods, apparatuses and systems may provide for technology that performs region-based motion estimation. More particularly, implementations relate to technology that provides accurate region-based motion compensation in order to improve video processing efficiency and/or video coding efficiency. 1. A system to perform efficient motion based video processing using region-based motion , comprising: obtain a plurality of block motion vectors for a plurality of blocks of a current frame with respect to a reference frame;', 'modify the plurality of block motion vectors, wherein the modification of the plurality of block motion vectors includes one or more of the following operations: smoothing of at least a portion of the plurality of block motion vectors, merging of at least a portion of the plurality of block motion vectors, and discarding of at least a portion of the plurality of block motion vectors;', 'segment the current frame into a plurality of regions, wherein the regions comprise a background region-type including a background moving region, and comprise a foreground region-type including a single foreground moving region in some instances and a plurality of foreground moving regions in other instances; and, 'a region-based motion analyzer, the region-based motion analyzer including one or more substrates and logic coupled to the one or more substrates, wherein the logic is toa power supply to provide power to the region-based motion analyzer.2. The system of claim 1 , wherein the logic is further to: 'restrict the modified plurality of block motion vectors by excluding a portion of the frame in some instances;', 'prior to the segmentation or the current frame into a plurality of regions compute a plurality of candidate region-based motion models individually for the background region-type and the foreground region-type based on the restricted-modified plurality of block motion vectors for the current frame with respect to the reference frame, wherein each ...

Подробнее
Номер записи: 21
08-05-2014 дата публикации

GEOMORPHING DEVICE

Номер: US20140125706A1
Автор: Kuboyama Shoichiro, Sakurai Satoshi
Принадлежит: Mitsubishi Electric Corporation

In the present invention, an input assembly unit () receives vertex information used before and after geomorphing and index information as input, and uses the index information to output vertex information used before and after the geomorphing of each polygon. A polygon processing unit () interpolates vertex information that has been processed at a vertex processing unit () in accordance with the time in order to perform output for each polygon. A rasterizing unit () detects pixels included in each polygon output by the polygon processing unit () within the output image in order to output pixel information in which the vertex information for the polygon has been interpolated in accordance with the position of each pixel. A pixel processing unit () determines the color of each pixel of the corresponding output image using the pixel information. 1. A geomorphing device comprising:an input assembler that receives, as an input, vertex information in which pieces of information showing vertices used before and after geomorphing are recorded without redundancy and pieces of index information used before and after geomorphing of each polygon, and that outputs pieces of vertex information used before and after the geomorphing of said each polygon by using said pieces of index information;a vertex processor that performs a predetermined vertex-associated process on the pieces of vertex information of said each polygon;a polygon processor that interpolates vertex information between the pieces of vertex information, on which said vertex-associated process is performed, according to time, and outputs the vertex information for each polygon;a rasterizer that detects each pixel included in each polygon outputted by said polygon processor in an output image, and that outputs the pixel as pixel information which is interpolated between the pieces of vertex information of the polygon according to a position of said each pixel detected thereby;a pixel processor that determines a ...

Подробнее
Номер записи: 22
03-03-2022 дата публикации

MEDICAL IMAGE PROCESSING APPARATUS, CONTROL METHOD FOR THE SAME, AND PROGRAM

Номер: US20220068470A1
Автор: Imasugi Yusuke, Sakamoto Tsuyoshi
Принадлежит:

A plurality of analysis functions each corresponding to an organ are managed, and organ information is stored in such a manner as to correlate with a corresponding type of analysis function. The organ information indicates which of a plurality of regions included in the organ is to be subjected to thinning. Specification of one of the analysis functions is received from a user, and medical image data is acquired. A plurality of regions of an organ included in the acquired medical image data are identified. The identified plurality of regions of the organ, a region to be subjected to thinning is determined on the basis of the stored organ information and the received type of the analysis function. Thinning is performed on the determined region of the organ. An image of the thinned region is displayed together with an image of a region not subjected to thinning.

Подробнее
Номер записи: 23
03-03-2022 дата публикации

IMAGING DEVICE, ELECTRONIC EQUIPMENT, AND IMAGING METHOD

Номер: US20220070349A1
Автор: WATANABE GOSHI
Принадлежит:

An imaging device, electronic equipment, and an imaging method capable of controlling a temperature rise are provided. The imaging device (CIS ) according to the present disclosure includes an imaging unit (), an information processing unit (DNN processing unit ), a temperature detection unit (), and a control unit (CIS control unit ). The imaging unit () captures an image and generates image data. The information processing unit. (DNN processing unit ) performs processing with respect to the image data read from the imaging unit (). The temperature detection unit () detects temperature. The control unit (CIS control unit ) changes the processing performed by the information processing unit (DNN processing unit ) according to the temperature detected by the temperature detection unit (). 1. An imaging device comprising:an imaging unit that captures an image and generates image data;an information processing unit that performs processing with respect to the image data read from the imaging unit;a temperature detection unit that detects temperature; anda control unit that changes the processing performed by the information processing unit according to the temperature detected by the temperature detection unit.2. The imaging device according to claim 1 , further comprisinga noise detection unit that detects noise included in the image data, whereinthe control unitcontrols an operation of the information processing unit according to the noise detected by the noise detection unit.3. The imaging device according to claim 1 , whereinthe information processing unit isa processing unit that performs DNN processing using a deep neural network (DNN) with respect to the image data, andthe control unitchanges a depth of layers of the DNN to be processed by the information processing unit.4. The imaging device according to claim 3 , whereinthe control unitchanges the DNN used by the information processing unit by making a selection from a plurality of the DNNs having different ...

Подробнее
Номер записи: 24
25-02-2021 дата публикации

SYSTEMS AND METHODS FOR PROCESSING ELECTRONIC MEDICAL IMAGES TO DETERMINE ENHANCED ELECTRONIC MEDICAL IMAGES

Номер: US20210056700A1
Автор: Chen Longquan, GYLLENHAAL EVAN, RAUNIYAR Niraj P.
Принадлежит: BOSTON SCIENTIFIC SCIMED, INC.

Systems and methods for processing electronic images from a medical device comprise receiving a first image frame and a second image frame from a medical device, and determining a region of interest by subtracting the first image frame from the second image frame, the region of interest corresponding to a visual obstruction in the first image frame and/or second image frame. Image processing may be applied to the first image frame and/or second image frame based on a comparison between a first area of the first image frame corresponding to the region of interest and a second area of the second image frame corresponding to the region of interest, and the first image frame and/or second image frame may be provided for display to a user. 1. A method for processing electronic images from a medical device , comprising:receiving a first image frame and a second image frame from a medical device;determining a region of interest by subtracting the first image frame from the second image frame, the region of interest corresponding to a visual obstruction in the first image frame and/or second image frame;applying image processing to the first image frame and/or second image frame based on a comparison between a first area of the first image frame corresponding to the region of interest and a second area of the second image frame corresponding to the region of interest; andproviding the first image frame and/or second image frame for display to a user.2. The method of claim 1 , wherein subtracting the first image frame from the second image frame comprises removing regions from consideration for the region of interest if the regions are similar beyond a predetermined threshold in both the first image frame and the second image frame.3. The method of claim 1 , wherein the visual obstruction comprises a reflection claim 1 , glare claim 1 , piece of debris claim 1 , and/or calculus.4. The method of claim 1 , further comprising:generating a grayscale first image frame based on ...

Подробнее
Номер записи: 25
13-02-2020 дата публикации

METHOD FOR PROCESSING IMAGES OF FINGERPRINTS

Номер: US20200050827A1
Автор: Kazdaghli Laurent
Принадлежит: IDEMIA IDENTITY & SECURITY FRANCE

A method for processing an image representing at least one finger supplied by an image sensor of the thin-film transistor type of a fingerprint-capture system is disclosed. The purpose of the method is to modify characteristics of the image so that they correspond to the characteristics of images acquired by a fingerprint-capture system using a CCD or CMOS sensor while preserving relevant information about the image. 1. A method for processing an image representing at least one finger supplied by an image sensor of the thin-film transistor type of a fingerprint capture system , said system comprising a transparent plate comprising a face on which each finger is placed and said image sensor is positioned so as to generate an image of each finger , wherein the method comprises:obtaining an image of each finger supplied by the image sensor, referred to as the first image;obtaining a second image by eliminating each continuous component of the first image;obtaining a third image by applying an averaging filter to the second image;applying a connected component analysis to the third image in order to define regions in said third image, each region comprising pixels having an identical value, referred to as the representative value;organising the regions in the form of a hierarchical tree in which the regions are organised in accordance with a parent-child relationship, a first region being the parent of a second region, which is then the child of the first region, when at least one pixel of the second region is adjacent to a pixel of the first region and a difference between the values representing the first and second regions is smaller than a difference between the values representing the first region and all other regions having at least one pixel adjacent to a pixel of the first region, the child region having a representative value smaller than its parent region;running through the hierarchical tree by order of increasing representative values and agglomerating each ...

Подробнее
Номер записи: 26
05-03-2015 дата публикации

CONVERSION OF DIGITAL IMAGES INTO DIGITAL LINE DRAWINGS

Номер: US20150063710A1
Автор: Klein Matthew N., Marlovics Dieter T., Rozzi William A.
Принадлежит:

Techniques described herein convert digital images into images suitable for use as coloring book pages and the like. The techniques include applying a smoothing operator to at least one channel image of a digital input image to form at least one smoothed image. A scaling operator is then applied to the at least one smoothed image to form at least one scaled image. A tone equalization operator is then applied to the at least one scaled image to form at least one equalized image. An edge detection operator is then applied to the at least one scaled image to form at least one edge image. In addition, a threshold operator is applied to the at least one edge image to form at least one threshold image. A digital line drawing is then created based at least in part on the at least one threshold image. 1. A method of converting a digital image to a digital line drawing , the method comprising:applying a smoothing operator to at least one channel image of a digital input image to form at least one smoothed image;applying a scaling operator to the at least one smoothed image to form at least one scaled image;applying a tone equalization operator to the at least one scaled image to form at least one equalized image;applying an edge detection operator to the at least one scaled image to form at least one edge image;applying a threshold operator to the at least one edge image to form at least one threshold image; andcreating a digital line drawing based at least in part on the at least one threshold image.2. The method of claim 1 , further comprising:forming a blank accumulator image from the input image;extracting the at least one channel image from the input image;combining the at least one threshold image with the blank accumulator image; andcreating the digital line drawing with the combined at least one threshold image and blank accumulator image.3. The method of claim 2 , wherein the at least one channel image is part of a subset of channel images.4. The method of claim 3 , ...

Подробнее
Номер записи: 27
21-02-2019 дата публикации

METHOD AND SYSTEM FOR DETECTING LINE DEFECTS ON SURFACE OF OBJECT

Номер: US20190057498A1
Автор: Bailey Kevin P., Ernst Jan, Panda Rameswar, Wu Ziyan
Принадлежит:

Method and system for detecting line defects on surface of object are presented. An imaging device captures images of surface of object under ambient and dark field illumination conditions. The images are processed with a plurality of image operations to detect areas of potential defects based on predictable pattern consisting of bright and shadow regions. Areas of potential defect are cut from processed images to sub images. Sub images are stitched together to generate hypotheses of potential defects at locations on surface of object. The hypotheses are classified to determine whether the potential defects are true defects at the locations. Line defect is detected by refining line segments detected on the processed image based on criteria. The criteria include distance from the true defects to the line segments and slops between the true defects and the line segments are less than threshold values. 1. A method for detecting a line defect on a surface of an object comprising:supporting the object on a platform;illuminating the surface of the object with a plurality of illumination sources comprising at least one ambient illumination source and at least one dark field illumination source;capturing images of the surface of the object under illumination conditions with the illumination sources using an imaging device;processing the captured images with a plurality of image operations using the image processor to detect areas of potential defects at locations on the surface of the object;cutting the areas of the potential defects from the processed images to sub images using the image processor;stitching the sub images at same location together to generate a set of hypotheses of the potential defects at the locations on the surface of the object using the image processor;classifying the hypotheses in the stitched images with a classifier to determine whether the potential defects are true defects using the image processor, wherein the classifier is trained with training ...

Подробнее
Номер записи: 28
22-05-2014 дата публикации

Parallel Approximation of Distance Maps

Номер: US20140139514A1
Автор: Alexander Bronstein, Michael Bronstein, Ofir Weber, Ron Kimmel, Yohai Devir
Принадлежит: Intel Benelux BV

Method for parallel approximation of distance maps on a discrete representation of a manifold, the method comprising: for at least one Euclidean grid applied on the discrete representation of a manifold, iterating over rows of the Euclidean grid in a first direction, and for each row currently visited during the iterating in the first direction, calculating a distance value for each single cell of the currently visited row in parallel, wherein the calculating is carried out according to a predefined approximation rule, using a distance value calculated for each one of respective cells of a row visited immediately before the currently visited row, wherein the cells of the row visited before the currently visited row are adjacent to the single cell in the Euclidean grid.

Подробнее
Номер записи: 29
04-03-2021 дата публикации

Fingerprint sensing method, fingerprint sensor, and display device including the same

Номер: US20210064839A1
Автор: Deok Hwa WOO, Dong Wook Yang, Hee Chul Hwang, Hyun Dae Lee, Seung Hyun Moon, Young Eun Lee
Принадлежит: Samsung Display Co Ltd

A fingerprint sensor includes a substrate, a light blocking layer that is on a first surface of the substrate and includes openings in a light blocking mask, and a sensor layer that is on a second surface of the substrate and includes photo sensors. A fingerprint sensing method of the fingerprint sensor includes: storing a calibration image; generating an original image, based on sensing signals from the photo sensors; performing calibration on the original image by utilizing the calibration image; and detecting a fingerprint, based on the calibrated image. The calibration image is generated by synthetizing valid regions extracted from an original calibration image corresponding to the original image.

Подробнее
Номер записи: 30
02-03-2017 дата публикации

OVARIAN FOLLICLE SEGMENTATION IN ULTRASOUND IMAGES

Номер: US20170061607A1
Автор: AZAR Reza Zahiri, Eskandari Hani, Pendziwol Linda
Принадлежит:

A method includes constructing a variation image from an ovarian follicle B-mode ultrasound image, wherein the variation image is indicative of local variations in the ovarian follicle B-mode ultrasound image, constructing a binary image from the variation image and the ovarian follicle B-mode image, identifying connected components in the binary image, wherein each connected component corresponds to a different ovarian follicle candidate, constructing a coarse follicle mask from the binary image where each identified connected component represents a mask for a corresponding different ovarian follicle candidate in the binary image, optimizing contours of the follicles in the coarse follicle mask, and segmenting one or more ovarian follicles from the ovarian follicle B-mode ultrasound image with the optimized follicle mask. 1. A method , comprising:constructing a variation image from an ovarian follicle B-mode ultrasound image, wherein the variation image is indicative of local variations in the ovarian follicle B-mode ultrasound image, and wherein the variation image includes one of a variance image and an entropy image;constructing a binary image from the variation image and the ovarian follicle B-mode image;identifying connected components in the binary image, wherein each connected component corresponds to a different ovarian follicle candidate;constructing a coarse follicle mask from the binary image where each identified connected component represents a mask for a corresponding different ovarian follicle candidate in the binary image;optimizing contours of the follicles in the coarse follicle mask; andsegmenting one or more ovarian follicles from the ovarian follicle B-mode ultrasound image with the optimized follicle mask.2. (canceled)3. The method of claim 1 , wherein constructing the binary image includes:setting a value of a pixel in the binary image to a value of one only if a first corresponding pixel in the variation image is less than a first ...

Подробнее
Номер записи: 31
03-03-2016 дата публикации

TECHNOLOGIES FOR IMPROVING THE ACCURACY OF DEPTH CAMERAS

Номер: US20160065930A1
Автор: CHANDRA Rohan, MALIK SHAHZAD A., RANJAN ABHISHEK
Принадлежит:

Technologies for improving the accuracy of depth camera images include a computing device to generate a foreground mask and a background mask for an image generated by a depth camera. The computing device identifies areas of a depth image of a depth channel of the generated image having unknown depth values as one of interior depth holes or exterior depth holes based on the foreground and background masks. The computing device fills at least a portion of the interior depth holes of the depth image based on depth values of areas of the depth image within a threshold distance of the corresponding portion of the interior depth holes. Similarly, the computing device fills at least a portion of the exterior depth holes of the depth image based on depth values of areas of the depth image within the threshold distance of the corresponding portion of the exterior depth holes. 125-. (canceled)26. A computing device for improving the accuracy of depth camera images , the computing device comprising:a mask generation module to (i) generate a foreground mask for an image generated by a depth camera, wherein the generated image includes a depth channel and the foreground mask includes at least one foreground object of the generated image, (ii) generate a background mask for the generated image, wherein the background mask includes portions of the generated image other than the at least one foreground object, and (iii) identify areas of a depth image of the depth channel of the generated image having unknown depth values as one of interior depth holes or exterior depth holes based on the foreground mask and the background mask; andan image filling module to (i) fill at least a portion of the interior depth holes of the depth image based on depth values of areas of the depth image within a threshold distance of the corresponding portion of the interior depth holes and (ii) fill at least a portion of the exterior depth holes of the depth image based on depth values of areas of the ...

Подробнее
Номер записи: 32
10-03-2016 дата публикации

Dynamic Waveform Region Enhancement

Номер: US20160071254A1
Автор: Bak Donald J.
Принадлежит:

A system and method includes reception of a color image comprising a plurality of color pixels, conversion of the color image to a monochromatic image comprising a plurality of monochromatic pixels, performance of M erosion operations on the monochromatic image to generate an eroded monochromatic image, where M is equal to or greater than one, performance of N dilation operations on the eroded monochromatic image to generate a mask image, where N is equal to or greater than one, identification of one or more regions of the mask image based on the mask image, and modification of regions of the color image corresponding to the identified regions of the mask image. 1. A system comprising: receive the image comprising a plurality of pixels;', 'locate one or more regions of interest within the image;', 'enhance the pixels in the one or more regions of interest to improve visibility of the pixels; and', 'modify the image to include the enhanced pixels and non-enhanced pixels in the image; and, 'an imaging processing unit for processing digital data representing an image comprising a patient electro-physiological waveform, wherein the imaging processing unit is configured toa display to display the modified image comprising the patient electro-physiological waveform with the enhanced pixels.2. The system according to claim 1 , wherein the image is embodied in a first video signal when received by the imaging processing unit and the modified image is embodied in a second video signal generated by the image processing unit for transmission to the display.3. The system according to claim 1 , wherein one or more of the pixels in the received image is color and wherein the image data processor enhances the pixels in the one or more regions of interest with a color enhancement operation.4. The system according to claim 1 , wherein the image further comprises at least one of a user interface element and a text information element.5. The system according to claim 1 , wherein the ...

Подробнее
Номер записи: 33
27-02-2020 дата публикации

METHOD AND APPARATUS FOR AUTOMATICALLY EXTRACTING IMAGE FEATURES OF ELECTRICAL IMAGING WELL LOGGING

Номер: US20200065606A1
Автор: FENG Zhou, LI NING, Li Yusheng, Liu Peng, Wang Chen, Wang Huafeng, WANG Kewen, WU Hongliang
Принадлежит:

A method and an apparatus for automatically extracting image features of electrical imaging well logging, wherein the method comprises the steps of: acquiring historical data of electrical imaging well logging; pre-processing the historical data of the electrical imaging well logging to generate an electrical imaging well logging image covering a full hole; recognizing and marking a typical geological feature in the electrical imaging well logging image covering the full hole, obtaining a processed image, and determining the processed image as a training sample according to types of the geological features; constructing a deep learning model including an input layer, a plurality of hidden layers, and an output layer; training the deep learning model using the training sample; using the trained deep learning model, recognizing type of a geological feature of an electrical imaging well logging image of a well section to be recognized, and performing morphological optimization processing on the recognition result to obtain a feature optimization recognition result. The solution can automatically, quickly and accurately recognize the typical geological features in the electrical imaging well logging image. 1. A method for automatically extracting image features of electrical imaging well logging , wherein the method comprises:acquiring historical data of electrical imaging well logging;pre-processing the historical data of the electrical imaging well logging to generate an electrical imaging well logging image covering a full hole;recognizing and marking a typical geological feature in the electrical imaging well logging image covering the full hole, obtaining a processed image, and determining the processed image as a training sample according to types of the geological features;constructing a deep learning model including an input layer, a plurality of hidden layers, and an output layer;training the deep learning model using the training sample to obtain a trained ...

Подробнее
Номер записи: 34
11-03-2021 дата публикации

METHOD AND SYSTEM FOR IMAGING AND IMAGE PROCESSING

Номер: US20210073959A1
Автор: Bronstein Alexander, ELMALEM Shay, GIRYES Raja, HAIM Harel, MAROM Emanuel
Принадлежит: Ramot at Tel-Aviv University Ltd.

A method of designing an element for the manipulation of waves, comprises: accessing a computer readable medium storing a machine learning procedure, having a plurality of learnable weight parameters. A first plurality of the weight parameters corresponds to the element, and a second plurality of the weight parameters correspond to an image processing. The method comprises accessing a computer readable medium storing training imaging data, and training the machine learning procedure on the training imaging data, so as to obtain values for at least the first plurality of the weight parameters. 1. A method of designing an element for the manipulation of waves , the method comprising:accessing a computer readable medium storing a machine learning procedure, having a plurality of learnable weight parameters, wherein a first plurality of said weight parameters corresponds to the element, and a second plurality of said weight parameters correspond to an image processing;accessing a computer readable medium storing training imaging data;training said machine learning procedure on said training imaging data, so as to obtain values for at least said first plurality of said weight parameters.2. The method according to claim 1 , wherein the element is a phase mask having a ring pattern claim 1 , and wherein said first plurality of said weight parameters comprises a radius parameter and a phase-related parameter.3. The method according to claim 1 , wherein said training comprises using backpropagation.4. The method according to claim 3 , wherein said backpropagation comprises calculation of derivatives of a point spread function (PSF) with respect to each of said first plurality of said weight parameters.5. The method according to claim 1 , wherein said training comprises training said machine learning procedure to focus an image.6. The method according to claim 5 , wherein said machine learning procedure comprises a convolutional neural network (CNN).7. The method according to ...

Подробнее
Номер записи: 35
11-03-2021 дата публикации

Motion Detection Method and Motion Detection System with Low Computational Complexity and High Detection Accuracy

Номер: US20210074001A1
Автор: Chan Shang-Lun, CHEN Shih-Tse, WU CHUN-CHANG, Yang Chao-Hsun
Принадлежит:

A motion detection method includes acquiring a raw image, detecting a motion object image according to the raw image by using a motion detector, cropping the raw image to generate a sub-image according to the motion object image, and inputting the sub-image to a processor for determining if a motion object of the sub-image matches with a detection category. The processor includes a neural network. The shape of the sub-image is a polygonal shape. 1. A motion detection method comprising:acquiring a raw image;detecting a motion object image according to the raw image by using a motion detector;cropping the raw image to generate a sub-image according to the motion object image; andinputting the sub-image to a processor for determining if a motion object of the sub-image matches with a detection category;wherein the processor comprises a neural network, and a shape of the sub-image is a polygonal shape.2. The method of claim 1 , further comprising:adjusting an aspect ratio of the motion object image after the motion object image is detected by the motion detector; andperforming at least one image processing operation to process a plurality of pixels of the motion object image for generating complete and continuous image pixel information;wherein an aspect ratio of the sub-image and the aspect ratio of the motion object image are identical, and the at least one image processing operation comprises an erosion processing operation, a dilation processing operation, and/or a connected component processing operation.3. The method of claim 1 , further comprising:inputting the raw image to the motion detector;partitioning the raw image into the motion object image and a background image by using the motion detector;wherein the motion object image belongs to a foreground image of the raw image.4. The method of claim 3 , wherein the foreground image has a first gray level claim 3 , the background image has a second gray level claim 3 , and the first gray level and the second gray ...

Подробнее
Номер записи: 36
15-03-2018 дата публикации

DETERMINING A POINTING VECTOR FOR GESTURES PERFORMED BEFORE A DEPTH CAMERA

Номер: US20180075294A1
Автор: Davies Robert L., Lee Chia-Hsun, Shahar Amit
Принадлежит: Intel Corporation

A pointing vector is determined for a gesture that is performed before a depth camera. One example includes receiving a first and a second image of a pointing gesture in a depth camera, the depth camera having a first and a second image sensor, applying erosion and dilation to the first image using a 2D convolution filter to isolate the gesture from other objects, finding the imaged gesture in the filtered first image of the camera, finding a pointing tip of the imaged gesture, determining a position of the pointing tip of the imaged gesture using the second image, and determining a pointing vector using the determined position of the pointing tip. 1. A method comprising:receiving a first and a second image of a pointing gesture in a depth camera, the depth camera having a first and a second image sensor;applying erosion and dilation to the first image using a 2D convolution filter to isolate the gesture from other objects;finding the imaged gesture in the filtered first image of the camera;finding a pointing tip of the imaged gesture;determining a position of the pointing tip of the imaged gesture using the second image; anddetermining a pointing vector using the determined position of the pointing tip.2. The method of claim 1 , wherein finding the imaged gesture comprises finding a hand.3. The method of claim 1 , wherein applying the filter comprises applying the filter to the second image of the depth camera.4. The method of claim 1 , wherein finding a pointing tip comprises finding a centroid of the imaged gesture and finding a point of the imaged gesture that is farthest from the centroid.5. The method of claim 4 , wherein the imaged gesture includes a hand and wherein finding a pointing tip further comprises:finding a second point farthest from the first point;selecting a point of the first point and second point which is farthest from an edge of the image; andselecting the point farthest from the edge as the pointing tip of a finger.6. The method of claim 1 , ...

Подробнее
Номер записи: 37
15-03-2018 дата публикации

Efficient acquisition of a target image from an original image

Номер: US20180075608A1
Автор: WEI Ding
Принадлежит: Alibaba Group Holding Ltd

An original image is acquired, where the original image comprises a target image. Image compression processing is performed on the original image according to a preset compression ratio, and a low-pixel image is created based on the image compression processing. Borderlines of the target image in the low-pixel image are determined. The determined borderlines of the low-pixel image are mapped into the original image, and a target image is created from the original image.

Подробнее
Номер записи: 38
24-03-2022 дата публикации

DIGITAL IMAGE GENERATION THROUGH AN ACTIVE LIGHTING SYSTEM

Номер: US20220092333A1
Автор: Flagg Matthew Willliam, Huber, JR. Richard Austin, Mallick Satya Prakash
Принадлежит:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an active lighting system. In one aspect, a method includes receiving a first image of the physical document having a first glare signature and a second image of the physical document having a second glare signature that is different from the first glare signature; determining a first glare map of the first image and a second glare map of the second image; comparing the first glare map to the second glare map; and generating the digital image based on the comparison of the first and second glare maps. 1. A computer-implemented method for providing a digital image of a physical document , the method comprising:receiving a first image of the physical document having a first glare signature and a second image of the physical document having a second glare signature that is different from the first glare signature;determining a first glare map of the first image and a second glare map of the second image;comparing the first glare map to the second glare map; andgenerating the digital image based on the comparison of the first and second glare maps.2. The computer-implemented method of claim 1 , wherein the first image is taken with a flash claim 1 , and wherein the second image is taken without a flash.3. The computer-implemented method of claim 1 , wherein the first image and the second image are taken in succession within a threshold temporal distance.4. The computer-implemented method of claim 1 , compromising:before determining the first glare map of the first image and the second glare map of the second image, aligning the first image and the second image based on the physical document.5. The computer-implemented method of claim 4 , wherein aligning the first image and the second image includes:estimating a homography using features from accelerated segment test (FAST) detector and an oriented FAST and rotated Binary Robust Independent Elementary Features (ORB) ...

Подробнее
Номер записи: 39
24-03-2022 дата публикации

INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND NON-TRANSITORY RECORDING MEDIUM

Номер: US20220092745A1
Автор: Ishikawa Ryo, Tanaka Toru
Принадлежит:

An information processing apparatus includes a first acquisition unit configured to acquire a first medical image of a target object and a second medical image of the target object captured at different time phases from each other, a second acquisition unit configured to acquire first contour information about the target object in the first medical image and second contour information about the target object in the second medical image, a generation unit configured to generate first processed information in which the first contour is blurred and second processed information in which the second contour is blurred, and a third acquisition unit configured to acquire deformation information about the target object between the first medical image and the second medical image based on the first processed information and the second processed information. 1. An information processing apparatus comprising:a first acquisition unit configured to acquire a first medical image of a target object and a second medical image of the target object captured at different time phases from each other;a second acquisition unit configured to acquire first contour information about a first contour being a boundary between the target object and a region outside the target object in the first medical image and second contour information about a second contour being a boundary between the target object and a region outside the target object in the second medical image;a generation unit configured to generate first processed information in which the first contour is blurred based on the first contour information or the second contour information and second processed information in which the second contour is blurred based on the first contour information or the second contour information; anda third acquisition unit configured to acquire deformation information about a deformation in the target object between the first medical image and the second medical image based on the first processed ...

Подробнее
Номер записи: 40
05-03-2020 дата публикации

IMAGE PROCESSING APPARATUS , IMAGE PROCESSING METHOD, AND COMPUTER READABLE RECORDING MEDIUM STORING PROGRAM

Номер: US20200074623A1
Автор: MATSUMOTO Hiroaki
Принадлежит: KONICA MINOLTA, INC.

An image processing apparatus includes: a hardware processor that: generates a thinned image by decreasing a pixel count on a medical image; inputs the thinned image to a neural network; extracts, using the neural network and from the thinned image, a signal component of a prescribed structure included in the medical image; and executes super-resolution processing on an output image outputted from the neural network to generate a structure image that expresses the signal component. The structure image includes a pixel count identical to the pixel count of the medical image. 1. An image processing apparatus comprising: generates a thinned image by decreasing a pixel count on a medical image;', 'inputs the thinned image to a neural network;', 'extracts, using the neural network and from the thinned image, a signal component of a prescribed structure included in the medical image; and', 'executes super-resolution processing on an output image from the neural network to generate a structure image that expresses the signal component, wherein the structure image comprises a pixel count identical to the pixel count of the medical image., 'a hardware processor that2. The image processing apparatus according to claim 1 , wherein executes upsampling processing on the output image; and', 'executes convolution processing on the output image that has been subjected to the upsampling processing, using a parameter that the neural network learns in advance, to extract the signal component and generate the structure image, wherein', 'the signal component comprises a high frequency component of the prescribed structure., 'the hardware processor further3. The image processing apparatus according to claim 1 , whereinthe neural network generates a plurality of output images as final output images,a number of the final output images is a square of a natural number “n,”{'sup': '2', 'a pixel count of the final output images is “1/n” of the pixel count of the medical image,'}the neural ...

Подробнее
Номер записи: 41
24-03-2016 дата публикации

IMAGE CAPTURE APPARATUS WHICH CONTROLS FRAME RATE BASED ON MOTION OF OBJECT, INFORMATION TRANSMISSION APPARATUS, IMAGE CAPTURE CONTROL METHOD, INFORMATION TRANSMISSION METHOD, AND RECORDING MEDIUM

Номер: US20160088219A1
Автор: Matsumoto Naoya
Принадлежит: CASIO COMPUTER CO., LTD.

An image capture apparatus includes an image capture unit a first communication unit and an image capture control unit The first communication unit receives data indicating a movement of a predetermined object from a sensor which is attached to the object. The image capture control unit controls a recording frame rate of a plurality of images captured by the image capture unit based on the data received by the first communication unit It is thereby possible with the image capture apparatus to control so as to be a recording frame rate of an image corresponding to a movement of an object, since it is possible to perform image capture control based on data indicating a movement of the object thus received. 1. An image capture apparatus comprising:an image capture unit;a reception unit that receives data indicating a movement of a predetermined object from a sensor which is attached to the object; anda control unit that controls a recording frame rate of a plurality of images captured by the image capture unit based on the data received by the reception unit.2. The image capture apparatus according to claim 1 , further comprising:a first acquisition unit that acquires a condition of the movement of the object based on the data indicating the movement of the object received by the reception unit,wherein the control unit controls the recording frame rate based on the condition of the movement of the object.3. The image capture apparatus according to claim 1 , further comprising:an estimation unit that estimates a behavior of the object from the data indicating the movement of the object,wherein the control unit controls the recording frame rate based on the behavior of the object which is estimated by the estimation unit.4. The image capture apparatus according to claim 3 ,wherein the estimation unit estimates the behavior of the object from data indicating the movement of the object, based on a timing of image capture processing by the image capture unit.5. The image ...

Подробнее
Номер записи: 42
31-03-2022 дата публикации

DATA AUGMENTATION INCLUDING BACKGROUND MODIFICATION FOR ROBUST PREDICTION USING NEURAL NETWORKS

Номер: US20220101047A1
Автор: Avadhanam Niranjan, Puri Nishant, Shetty Rajath, Sivaraman Sakthivel
Принадлежит:

In various examples, a background of an object may be modified to generate a training image. A segmentation mask may be generated and used to generate an object image that includes image data representing the object. The object image may be integrated into a different background and used for data augmentation in training a neural network. Data augmentation may also be performed using hue adjustment (e.g., of the object image) and/or rendering three-dimensional capture data that corresponds to the object from selected views. Inference scores may be analyzed to select a background for an image to be included in a training dataset. Backgrounds may be selected and training images may be added to a training dataset iteratively during training (e.g., between epochs). Additionally, early or late fusion nay be employed that uses object mask data to improve inferencing performed by a neural network trained using object mask data. 1. A method comprising:identifying, in a first image, a region that corresponds to an object having a first background in the first image;determining image data representative of the object based at least on the region of the object;generating a second image that includes the object having a second background based at least on integrating, using the image data, the object with the second background; andtraining at least one neural network to perform a predictive task using the second image.2. The method of claim 1 , wherein the identifying of the region comprises determining at least a first segment of the first image corresponds to the object and at least a second segment of the first image corresponds to the first background based at least on performing image segmentation on the first image.3. The method of claim 1 , wherein the training of the at least one neural network is to classify one or more poses of the objects.4. The method of claim 1 , wherein the determining the image data comprises generating a mask based at least on the region in the ...

Подробнее
Номер записи: 43
23-03-2017 дата публикации

MULTI-VIEW DISPLAYS AND ASSOCIATED SYSTEMS AND METHODS

Номер: US20170085867A1
Автор: Baran Thomas Anthony, Hirsch Matthew Waggener, Leithinger Daniel
Принадлежит:

Techniques for controlling optical behavior of a multi-view display apparatus comprising a first layer comprising first optical elements and a second layer comprising second optical elements. The techniques include obtaining a plurality of scene views; obtaining information specifying a model of the multi-view display apparatus; obtaining information specifying at least one blurring transformation; and generating actuation signals for controlling the multi-view display apparatus to concurrently display a plurality of display views corresponding to the plurality of scene views, the actuation signals comprising first actuation signals for controlling the first optical elements and second actuation signals for controlling the second optical elements, the generating comprising: generating the first actuation signals and the second actuation signals based, at least in part, on the plurality of scene views, the information specifying the model of the multi-view display apparatus, and the information specifying the at least one blurring transformation. 1. A system for generating actuation signals to control optical behavior of a multi-view display apparatus , the multi-view display apparatus comprising at least two different layers including a first layer comprising a first plurality of optical elements and a second layer comprising a second plurality of optical elements , the system comprising:at least one processor; obtaining a plurality of scene views;', 'obtaining information specifying a model of the multi-view display apparatus;', 'obtaining information specifying at least one blurring transformation; and', 'generating the first plurality of actuation signals and the second plurality of actuation signals based, at least in part, on the plurality of scene views, the information specifying the model of the multi-view display apparatus, and the information specifying the at least one blurring transformation.', 'generating a plurality of actuation signals for controlling ...

Подробнее
Номер записи: 44
31-03-2016 дата публикации

IMAGE CAPTURING APPARATUS AND CONTROL METHOD THEREFOR, AND STORAGE MEDIUM

Номер: US20160094777A1
Автор: Takao Yumi
Принадлежит:

An image capturing apparatus includes: an image sensor having a plurality of pixels arranged two-dimensionally; a readout unit that reads out, from the pixels of the image sensor, signals for focus detection by thinning out pixels at a cycle corresponding to a predetermined pixel interval or adding the thinned-out pixels; a focus detection unit that detects an in-focus position of an imaging lens based on the signals for focus detection read out by the readout unit; a determination unit that determines whether or not a focus detection result of the focus detection unit varies depending on a phase of the thinning out or adding carried out when reading out the signals for focus detection; and a correction unit that corrects the focus detection result of the focus detection unit based on a determination result of the determination unit. 1. An image capturing apparatus comprising:an image sensor having a plurality of pixels arranged two-dimensionally;a readout unit that reads out, from the pixels of the image sensor, signals for focus detection by thinning out pixels at a cycle corresponding to a predetermined pixel interval or adding the pixels;a focus detection unit that detects an in-focus position of an imaging lens based on the signals for focus detection read out by the readout unit;a determination unit that determines whether or not a focus detection result of the focus detection unit varies depending on a phase of the thinning out or adding carried out when reading out the signals for focus detection; anda correction unit that corrects the focus detection result of the focus detection unit based on a determination result of the determination unit.2. The image capturing apparatus according to claim 1 ,wherein a color filter is arranged on each of the plurality of pixels, and the readout unit reads out signals of pixels corresponding to a single color of the color filters as the signals for focus detection.3. The image capturing apparatus according to claim 2 , ...

Подробнее
Номер записи: 45
19-03-2020 дата публикации

TRAINING IMAGE-PROCESSING NEURAL NETWORKS BY SYNTHETIC PHOTOREALISTIC INDICIA-BEARING IMAGES

Номер: US20200089998A1
Автор: Borin Pavel Valeryevich, Zagaynov Ivan Germanovich
Принадлежит:

Systems and methods for training image processing neural networks by synthetic photorealistic indicia-bearing images. An example method comprises: generating an initial set of images, wherein each image of the initial set of images comprises a rendering of a text string; producing an augmented set of images by processing the initial set of images to introduce, into each image of the initial set of image, at least one simulated image defect; generating a training dataset comprising a plurality of pairs of images, wherein each pair of images comprises a first image selected from the initial set of images and a second image selected from the augmented set of images; and training, using the training dataset, a convolutional neural network for image processing. 1. A method , comprising:generating, by a computer system, an initial set of images, wherein each image of the initial set of images comprises a rendering of a text string;producing an augmented set of images by processing the initial set of images to introduce, into each image of the initial set of image, at least one simulated image defect;generating a training dataset comprising a plurality of pairs of images, wherein each pair of images comprises a first image selected from the initial set of images and a second image selected from the augmented set of images; andtraining, using the training dataset, a convolutional neural network for image processing.2. The method of claim 1 , wherein processing the initial set of images further comprises:superimposing, on a generated image, a transparent image of a pre-defined or randomly generated text.3. The method of claim 1 , wherein processing the initial set of images further comprises:de-contrasting a generated image to reduce a maximum difference in luminance of pixels of the generated image by a pre-defined value.4. The method of claim 1 , wherein processing the initial set of images further comprises:simulating an additional light source in a scene of a generated ...

Подробнее
Номер записи: 46
19-03-2020 дата публикации

METHOD AND APPARATUS FOR RESTORING IMAGE

Номер: US20200090306A1
Автор: CHO Yang Ho, KANG Deokyoung, Nam Dong Kyung
Принадлежит: SAMSUNG ELECTRONICS CO., LTD.

Provided is an image restoration apparatus and method. The image restoration apparatus may store an image restoration model including a convolutional layer corresponding to kernels having various dilation gaps, and may restore an output image from a target image obtained by rearranging a compound eye vision (CEV) image by the image restoration model. 1. An image restoration method comprising:acquiring a target image by rearranging an input image of an object; andrestoring an output image from the acquired target image, based on an image restoration model comprising a convolutional layer corresponding to a kernel having a dilation gap.2. The image restoration method of claim 1 , wherein the restoring the output image comprises restoring the output image based on the convolutional layer corresponding to a plurality of kernels corresponding to a plurality of dilation gaps claim 1 , respectively claim 1 ,wherein the plurality of dilation gaps are determined based on a configuration of lenses included in an image sensor and sensing elements included in the image sensor.3. The image restoration method of claim 1 , wherein the dilation gap is determined based on a configuration of sensing elements included in an image sensor and a distance between the image sensor and a point of the object spaced apart from the image sensor.4. The image restoration method of claim 1 , wherein the kernel is determined based on a position relationship of a plurality of sensing elements included in an image sensor that are configured to receive rays radiated from a point of the object spaced apart from the image sensor by a distance greater than a threshold distance.5. The image restoration method of claim 1 , wherein the image restoration model comprises a convolutional layer corresponding to a kernel determined based on a position relationship of a plurality of sensing elements included in an image sensor that are configured to receive rays radiated from a point spaced apart from the image ...

Подробнее
Номер записи: 47
07-04-2016 дата публикации

Graphics Processing Method and System

Номер: US20160098845A1
Автор: AMELINE Ian R., BLAIS Eric A.
Принадлежит:

The embodiments discussed herein involve flood filling a region with anti-aliasing. In forming a fill region, a candidate pixel can be included in the region based on a color of the pixel and also a color of a neighbor of the point. The inclusion basis may be a color distance between a seed color and the points, and a color distance between the seed color and the point's neighbor. Points in the region may be weighted according to their color distance relative to the seed color, where the color distance can also take into account alpha values. Flood filling may be anti-aliased by assigning alpha values to pixels in gaps between corners of the fill region, where an alpha value may be proportional to a point's contribution to the gap. Dimples in a fill region may be tested for and used to determine which of two flood fill algorithms to use. 1. A method of performing a flood fill operation on an image , the method comprising: filling a region of the image based on a test for noise in the region.2. A method according to claim 1 , wherein the test comprises a ratio or number of pixels in the region whose vertically opposing neighbor pixels or horizontally opposing neighbor pixels differ in color or differ in color within a given tolerance.3. A method according to wherein the test for noise is accomplished by counting pixels which have two differing neighbor pixels in the horizontal direction claim 1 , or two differing neighbor pixels in the vertical direction claim 1 , and determining whether to pass or fail the test based on the result of this count.4. A method of performing a flood fill on an image claim 1 , the method comprising: determining image points to be flood filled based on the color of a seed point; and deblending this seed color from image points among the image points to be filled claim 1 , where an image point is deblended based on its color and based on the seed color.5. A method according to claim 4 , wherein the deblending comprises extrapolating using ...

Подробнее
Номер записи: 48
05-04-2018 дата публикации

SYSTEM AND METHOD PROVIDING AUTOMATIC ALIGNMENT OF AERIAL/SATELLITE IMAGERY TO KNOWN GROUND FEATURES

Номер: US20180096451A1
Автор: HERENA ULLOA Zazhil Ha, Misra Avishkar, Ravada Siva, REYES MARTINEZ Juan Carlos
Принадлежит:

Systems, methods, and other embodiments are disclosed for correcting errors in the geo-spatial locations of acquired image data. In one embodiment, acquired aerial or satellite image data is segmented to generate extracted boundary data. The extracted boundary data represents boundaries of features of a portion of the Earth's surface, but at incorrect geo-spatial coordinates. The extracted boundary data is matched to expected boundary data derived from ground truth data. The expected boundary data represents boundaries of the features at correct geo-spatial coordinates. Adjustment parameters are generated that represent a geo-spatial misalignment between the extracted boundary data and the expected boundary data. Metadata in a header of the acquired image data is modified to include the adjustment parameters. The adjustment parameters may be applied to the acquired image data to generate corrected image data at correct geo-spatial coordinates. 1. A computer-implemented method performed by a computing device where the computing device includes at least a processor for executing instructions from a memory , the method comprising:segmenting, via at least the processor, acquired image data to generate extracted boundary data, where the acquired image data is one of aerial image data or satellite image data representing features of a portion of the Earth's surface at incorrect geo-spatial coordinates, and where the extracted boundary data represents boundaries of the features at the incorrect geo-spatial coordinates;matching, via at least the processor, the extracted boundary data to expected boundary data derived from a set of ground truth data, where the expected boundary data represents the boundaries of the features at correct geo-spatial coordinates;estimating, via at least the processor, adjustment parameters representing an amount and a type of a geo-spatial misalignment between the extracted boundary data and the expected boundary data;applying, via at least the ...

Подробнее
Номер записи: 49
12-05-2022 дата публикации

METHODS OF YIELD ASSESSMENT WITH CROP PHOTOMETRY

Номер: US20220148151A1
Автор: BERGHOEFER CHAD CLIFFORD, HANSELMAN TRAVIS ALLEN, Hausmann Neil J., MESSINA CARLOS
Принадлежит: PIONEER HI-BRED INTERNATIONAL, INC.

A method of evaluating one or more kernels of an ear of maize using digital imagery that includes acquiring a digital image of the one or more kernels of the ear of maize without the use of spatial reference points, processing the digital image to estimate at least one physical property of the one or more kernels of the ear of maize from the digital image, and evaluating the at least one kernel of maize using the estimate of the at least one physical property of the at least one kernel of maize. The method includes using one or more such digital images to estimate yield on a plant, management zone, field, county and country level. 1. A method of predicting total yield of a corn crop , comprising:obtaining a plurality of images of an ear of corn without the use of spatial reference points,determining the number of kernels per ear, andcalculating predicted total yield or test weight based on the image, wherein the predicted total yield or test weight is calculated based on an estimate of the number of total ears in the area of the predicted total yield or test weight, which number of total ears is based on one or more of as-planted data, historical information about the variety planted, an aerial image of the plants, rainfall or crop moisture data.2. The method of claim 1 , wherein an image of the corn ear is positioned within a target window on the viewing screen of an imaging device.3. The method of claim 2 , wherein the plurality of images are still images from a video feed of the corn ear.4. The method of claim 2 , wherein the images are selected based on having a corn ear to target window surface area ratio between 70% to 90%.5. The method of claim 4 , wherein the corn kernels on the corn ear are segmented and counted.6. The method of claim 1 , wherein the number of kernels per ear is the median number of kernels from a set of still images.7. The method of claim 1 , wherein the image is a two dimensional image and the total number of kernels per ear is obtained ...

Подробнее
Номер записи: 50
08-04-2021 дата публикации

Foreign Material Inspection System

Номер: US20210100256A1
Автор: KNUDSEN Kyle N., YOUNGS Jeff
Принадлежит: Prospection Solutions, LLC

A first conveyor for conveying foodstuff, a second conveyor separated from the first conveyor by a gap of free space, a top camera positioned above the gap and above the first conveyor and the second conveyor, a bottom camera positioned below the gap and below the first conveyor and the second conveyor, wherein the top camera and the bottom camera capture images of the foodstuff in the gap between the first conveyor and the second conveyor for analysis. 1. A foodstuff inspection system , comprising:a first conveyor for conveying foodstuff;a second conveyor separated from the first conveyor by a gap of free space;a top camera positioned above the gap and above the first conveyor and the second conveyor;a bottom camera positioned below the gap and below the first conveyor and the second conveyor;wherein the top camera and the bottom camera capture images of the foodstuff in the gap between the first conveyor and the second conveyor for analysis.2. The food inspection system of claim 1 , and further comprising a processor connected to the top camera and the bottom camera for processing images taken of the foodstuff for detection of foreign debris in the foodstuff.3. The food inspection system of claim 2 , and further comprising a library communicatively coupled to the processor containing data representative of acceptable pixels corresponding to images of foodstuff wherein the processor compares images of the foodstuffs on a pixel by pixel basis with the data representative of acceptable pixels stored in the library to detect foreign debris.4. The food inspection system of claim 3 , wherein the processor conducts a morphological operation on the image of the foodstuff to emphasize foreign debris before the processor compares the image of the foodstuff.5. The food inspection system of claim 4 , wherein the morphological operation comprises image dilation to make foreign debris more visible.6. The food inspection system of claim 5 , wherein the processor scans the image ...

Подробнее
Номер записи: 51
14-04-2016 дата публикации

Method and apparatus for determining a detection of a defective object in an image sequence as a misdetection

Номер: US20160104269A1
Автор: Oliver Theis
Принадлежит: Thomson Licensing SAS

Results of automatic detection of dirt or other non-steady defects in a sequence of digitized image frames can be unreliable. Here, a determination of a detection of a defective object to be replaced by a replacement pattern in a frame of a sequence of image frames as a misdetection is presented that comprises determining a value of a first similarity measure between a boundary of the detected defective object and a boundary of the replacement pattern and determining a value of a second similarity measure between the detected defective object and the replacement pattern. The detection of the defective object is determined as a misdetection if at least one of the following holds true: the value of the first similarity measure is outside of a corresponding first similarity acceptance range and the value of the second similarity measure is inside of a corresponding second similarity acceptance range.

Подробнее
Номер записи: 52
14-04-2016 дата публикации

IMAGE BASED OBJECT LOCATOR

Номер: US20160104290A1
Автор: Patnaik Rohit
Принадлежит:

Techniques, systems, and devices are disclosed for analyzing a reconstructed charged particle image of a volume of interest from charged particle detector measurements to determine a location and boundaries of one or more objects or an orientation of the one or more objects. The technique can include performing a segmentation operation on the reconstructed charged particle image of the volume. The segmentation operation identifies a subset of a set of voxels of the image of the volume as object candidate voxels. The technique can include locating corners of the one or more objects to determine the location, boundaries, or the orientation of the one or more objects. The technique can also include the computation of the center of mass of the one or more objects. The technique can include performing a morphological operation on the image and can include performing a connected-component analysis on the identified object-candidate voxels. 1. A method for analyzing a reconstructed charged particle image of a volume from charged particle detector measurements to determine a location and boundaries of one or more objects associated with the volume , the method comprising:performing a segmentation operation on the reconstructed charged particle image of the volume, wherein the segmentation operation identifies a subset of a set of voxels of the reconstructed charged particle image of the volume as object candidate voxels; and determine the location, boundaries and corners of the one or more objects.2. The method of claim 1 , wherein the one or more objects include at least one container; andwherein determining the location, boundaries and corners of the one or more objects includes determining location, boundaries and corners of the at least one container in addition to location, boundaries and corners of contents of the at least one container.3. The method of claim 1 , wherein the one or more objects include at least one package; andwherein determining the location, ...

Подробнее
Номер записи: 53
26-03-2020 дата публикации

Bidirectional Edge Highlighting With Strong Edge Attentuation

Номер: US20200098093A1
Автор: Fleizach Gregory K.
Принадлежит: United States of America, as Represented by the Secretary of the Navy

A method and system for bidirectional edge highlighting. A memory receives an original input image. A processor calculates edge intensity for each edge pixel in the original input image. The processor also identifies strong edges and attenuates said strong edges. The processor can further determine whether the attenuated strong edges should be bright or dark based on the intensity of the pixel in the original image. The processor applies bidirectional edge highlighting to the image based on the intensity of the pixel in the original image. The degree of darkness or brightness of the highlighting is based on the calculated edge intensity after strong edge attenuation. 1. A method for bidirectional edge highlighting with edge attenuation , the method comprising:receiving, at a memory device, an original input image;calculating, by a processor, an edge intensity for each pixel in the original input image;identifying, by the processor, the edge pixel as a strong edge pixel in the original input image when the calculated edge intensity exceeds an edge strength threshold, including by assigning, by the processor, a pixel value of one to each strong edge pixel, wherein the identifying step further includes assigning, by the processor, a pixel value of zero to each edge pixel when the calculated edge intensity is equal to or less than the edge strength threshold, wherein the assigning steps thus binarize an edge strength result;attenuating, by the processor, said strong edge pixels in the original input image, thereby producing a transformed image, wherein the attenuating step includes multiplying, by the processor, an attenuation factor by the calculated edge intensity for each said strong edge pixel;determining, by the processor, whether the attenuated strong edge pixels in the transformed image should be bright or dark based on an intensity of each pixel in the original input image; and,applying, by the processor, bidirectional edge highlighting to the transformed image ...

Подробнее
Номер записи: 54
26-03-2020 дата публикации

IDENTIFICATION AND REDESIGN OF CRITICAL THIN SEGMENTS BELOW 3D PRINTER RESOLUTION

Номер: US20200098195A1
Автор: Arisoy Erhan, Jaiswal Prakhar, Madeley David, Musuvathy Suraj Ravi
Принадлежит:

Systems and methods may support identification and redesign of critical thin segments in a 3D model that are below 3D printer resolution. Identification of critical thin segments may include segmenting cross-sectional slices of the 3D model into printable segments and non-printable segments and using a machine learning model trained using geometrical features computed on thin regions to classify the non-printable segments as critical or non-critical. Redesign of critical thin segments may include thickening the critical thin segments such that the segment size of the critical thin segments satisfy a thickening criterion with respect to the printer resolution and smoothing sharp corners added to the cross-sectional slice at an intersection between the critical thin segment and a neighboring printable segment. Redesign of the critical thin segments may account for tolerable overhang. 1. A method comprising:accessing a three-dimensional (3D) model representative of an object to be constructed by a 3D printer;extracting a cross-sectional slice of the 3D model perpendicular to a build direction for construction of the object by the 3D printer; segmenting the cross-sectional slice into printable segments and non-printable segments; and', 'using a machine learning model trained using geometrical features computed on thin regions to classify each of the non-printable segments as critical or non-critical; and, 'identifying a critical thin segment in the cross-sectional slice with a segment size smaller than a printer resolution of the 3D printer, wherein identifying comprisesmodifying the 3D model by thickening the critical thin segment such that the segment size of the critical thin segment satisfies a thickening criterion with respect to the printer resolution; andproviding the modified 3D model to the 3D printer for construction of the object.2. The method of claim 1 , wherein thickening the critical then segment comprises:incrementally thickening the critical thin ...

Подробнее
Номер записи: 55
21-04-2016 дата публикации

SELF-PORTRAIT ENHANCEMENT TECHNIQUES

Номер: US20160110848A1
Автор: Gray Douglas Ryan, Lin Xiaofan, TAYLOR COLIN JON
Принадлежит:

Systems and approaches are provided for optimizing self-portraiture. The background of the self-portrait can be enhanced by image registration or stitching techniques of images captured using one or more conventional cameras. Multiple standard resolution images can be stitched together to generate a panoramic or a composite image of a higher resolution. Foreground elements, such as one or more representations of users, can also be enhanced in various ways. The representations of the users can be composited to exclude undesirable elements, such as image data of one of the users extending her arm to capture the self-portrait. An ideal pose of the users can automatically be selected and other image enhancements, such as histogram optimization, brightness and contrast optimization, color-cast correction, or reduction or removal of noise, can automatically be performed to minimize user effort in capturing self-portraits. 1. A computer-implemented method , comprising:obtaining a plurality of images;determining one or more background elements from the plurality of images;determining a plurality of foreground elements from the plurality of images;generating a background image comprising a first composite of at least a portion of the one or more background elements;ranking the plurality of foreground elements according to one or more visual characteristics; andgenerating a self-portrait image, the self-portrait image comprising at least one of the plurality of foreground elements based on the ranking of the plurality of foreground elements and the background image.2. The computer-implemented method of claim 1 , further comprising:displaying the plurality of foreground elements as a ranked list; andreceiving a selection of the at least one of the plurality of foreground elements.3. The computer-implemented method of claim 1 , wherein the plurality of foreground elements include at least a portion of representations of one or more users.4. The computer-implemented method of ...

Подробнее
Номер записи: 56
20-04-2017 дата публикации

Computer-implemented methods, computer-readable media, and systems for tracking a plurality of spermatozoa

Номер: US20170109879A1
Автор: Leonardo Urbano, Matthew Vermilyea, Moshe Kam, Puneet Masson
Принадлежит: DREXEL UNIVERSITY, University of Pennsylvania Penn

One aspect of the invention provides a computer-implemented method for tracking a plurality of spermatozoa. The method includes: identifying a coordinate for each of the plurality of spermatozoa in a plurality of video frames; and applying a nearest-neighbor joint probabilistic data association filter (NN-JPDAF) algorithm to associate the coordinates with one or a plurality of sperm tracks. Another aspect of the invention provides a non-transitory computer-readable medium containing program instructions executable by a processor. The computer-readable medium can include program instructions for performing a method as described herein. Another aspect of the invention provides a system including: a processor and a computer-readable medium including program instructions for performing a method as described herein.

Подробнее
Номер записи: 57
29-04-2021 дата публикации

ACTION DETECTION DURING IMAGE TRACKING

Номер: US20210124940A1
Автор: Krishnamurthy Sailesh Bharathwaaj, MIRZA Shahmeer Ali, Paul Deepanjan, Vakacharla Sarath
Принадлежит:

A system includes a sensor, a weight sensor, and a tracking subsystem. The tracking subsystem receives an image feed of top-view images generated by the sensor and weight measurements from the weight sensor. The tracking subsystem detects an event associated with an item being removed from a rack in which the weight sensor is installed. The tracking subsystem determines that a first person or a second person may be associated with the event. In response to determining that the first or second person may be associated with the event, buffer frames are stored of top-view images generated by the sensor during a time period associated with the event. The tracking subsystem then determines, using at least one of the stored buffer frames and a first action-detection algorithm, whether an action associated with the event was performed by the first person or the second person. 1. A system , comprising:a sensor positioned above a rack in a space, the sensor configured to generate top-view images of at least a portion of a space comprising the rack, wherein the rack comprises a shelf storing at least one item;and receive an image feed comprising frames of the top-view images generated by the sensor;', 'detect an event associated with a portion of a person entering a zone adjacent to the rack in conjunction with the at least one item being removed from the shelf;', 'in response to detecting the event, determine that a first person or a second person may be associated with the detected event;', 'in response to determining that the first or second person may be associated with the detected event, store buffer frames of top-view images generated by the sensor during a time period associated with the detected event;', 'determine, using at least one of the stored buffer frames and a first action-detection algorithm, whether an action associated with the detected event was performed by the first person or the second person, wherein the first action-detection algorithm is configured ...

Подробнее
Номер записи: 58
29-04-2021 дата публикации

IMAGE-BASED ACTION DETECTION USING CONTOUR DILATION

Номер: US20210125341A1
Автор: Krishnamurthy Sailesh Bharathwaaj, MIRZA Shahmeer Ali, Paul Deepanjan, Vakacharla Sarath
Принадлежит:

A system includes a sensor, a weight sensor, and a tracking subsystem. The tracking subsystem receives an image feed of top-view images generated by the sensor and weight measurements from the weight sensor. The tracking subsystem detects an event associated with an item being removed from a rack in which the weight sensor is installed. The tracking subsystem determines that a first person and a second person may be associated with the event. In response, the tracking subsystem dilates contours associated with the first and second person from a first depth to a second depth until the contours enter a zone adjacent to the rack. A number of iterations is determined for each contour to enter the zone adjacent to the rack. If the first person's contour enters the zone in fewer iterations, the item is assigned to the first person. 1. A system , comprising:a sensor positioned above a rack in a space, the sensor configured to generate top-view depth images of at least a portion of a space comprising the rack;a plurality of weight sensors, each weight sensor associated with a corresponding item stored on a shelf of the rack; and receive an image feed comprising frames of the top-view depth images generated by the sensor;', 'receive weight measurements from the weight sensors;', 'detect an event associated with one or both of a portion of a person entering a zone adjacent to the rack and a change of weight associated with a first item being removed from a first shelf associated with a first weight sensor;', 'in response to detecting the event, determine that a first person and a second person may be associated with the detected event, based on one or more of a first distance between the first person and the rack, a second distance between the second person and the rack, and an inter-person distance between the first person and the second person;', 'in response to determining that the first and second person may be associated with the detected event, access a first top-view ...

Подробнее
Номер записи: 59
02-04-2020 дата публикации

Image processing apparatus identifying pixel which satisfies specific condition and performing replacement process on pixel value of identified pixel

Номер: US20200106925A1
Автор: Masaya Takasu, Ryuji Yamada
Принадлежит: Brother Industries Ltd

In an image forming apparatus, a processor acquires target image data representing a target image. The processor identifies as a first type pixel in the target image, and sets a target pixel from among peripheral pixels of the pixel identified as the first type pixel. The processor identifies the target pixel as a second type pixel in a case where the target pixel satisfies a specific condition. The processor generates processed image data by performing a replacement process in which a pixel value of the pixel identified as the first type pixel is replaced with a first value representing a first color and a pixel value of the pixel identified as the second type pixel is replaced with a second value representing a second color. The specific condition includes a condition that all specific pixels in a specific range match a specific pattern.

Подробнее
Номер записи: 60
28-04-2016 дата публикации

IMAGING DEVICE, IMAGING METHOD, AND IMAGE PROCESSING DEVICE

Номер: US20160119603A1
Автор: HAYASHI Kenkichi, IRIE Kosuke, NARUSE Yousuke, SUGIMOTO Masahiko
Принадлежит: FUJIFILM Corporation

An imaging device according to an aspect of the present invention includes: an image generation section that generates a moving image; a filter acquisition section that acquires a restoration filter corresponding to a transfer function for the point distribution of an optical system; an aperture value detection section that detects an aperture value of the optical system; a restoration processing determination section that determines whether or not the aperture value detected by the aperture value detection section is equal to or greater than a small-aperture-blurring reference aperture value; and a restoration processing execution section that executes the restoration processing on the moving image through the restoration filter, in case where the restoration processing determination section determines that the aperture value detected by the aperture value detection section is equal to or greater than the small-aperture-blurring reference aperture value. 1. An imaging device comprising:an imaging section that captures an image of a subject through an optical system and generates image data;an image generation section that generates a moving image subjected to thinning-out processing on the basis of the image data;a filter acquisition section that acquires a restoration filter corresponding to a transfer function for point distribution of the optical system;an aperture value detection section that detects an aperture value of the optical system when the imaging section captures the image of the subject;a restoration processing determination section that determines whether or not the aperture value detected by the aperture value detection section is a distortion-suppression aperture value as an aperture value corresponding to small-aperture blurring which suppresses aliasing distortion caused when the thinning-out processing is performed; anda restoration processing execution section that executes the restoration processing on the moving image, which is subjected to ...

Подробнее
Номер записи: 61
18-04-2019 дата публикации

SUBTITLE EXTRACTION METHOD AND DEVICE, STORAGE MEDIUM

Номер: US20190114486A1
Автор: WANG Xingxing
Принадлежит:

A subtitle extraction method includes decoding a video to obtain video frames; performing adjacency operation in a subtitle arrangement direction on pixels in the video frames to obtain adjacency regions in the video frames; and determining certain video frames including a same subtitle based on the adjacency regions, and subtitle regions in the certain video frames including the same subtitle based on distribution positions of the adjacency regions in the video frames including the same subtitle. The method also includes constructing a component tree for at least two channels of the subtitle regions and using the constructed component tree to extract a contrasting extremal region corresponding to each channel; performing color enhancement processing on the contrasting extremal regions of the at least two channels to form a color-enhanced contrasting extremal region; and extracting the subtitle by merging the color-enhanced contrasting extremal regions of at least two channels. 1. A subtitle extraction method , comprising:decoding a video to obtain video frames;performing adjacency operation in a subtitle arrangement direction on pixels in the video frames to obtain adjacency regions in the video frames;determining certain video frames including a same subtitle based on the adjacency regions in the video frames, and subtitle regions in the certain video frames including the same subtitle based on distribution positions of the adjacency regions in the video frames including the same subtitle;constructing a component tree for at least two channels of the subtitle regions, and using the constructed component tree to extract a contrasting extremal region corresponding to each channel;performing color enhancement processing on the contrasting extremal regions of the at least two channels, to form a color-enhanced contrasting extremal region; andextracting the subtitle by merging the color-enhanced contrasting extremal regions of at least two channels.2. The method ...

Подробнее
Номер записи: 62
18-04-2019 дата публикации

Predicting Patch Displacement Maps Using A Neural Network

Номер: US20190114818A1
Автор: Lin Zhe, Lu Xin, Shen Xiaohui, Yang Jimei, YU Jiahui
Принадлежит: ADOBE SYSTEMS INCORPORATED

Predicting patch displacement maps using a neural network is described. Initially, a digital image on which an image editing operation is to be performed is provided as input to a patch matcher having an offset prediction neural network. From this image and based on the image editing operation for which this network is trained, the offset prediction neural network generates an offset prediction formed as a displacement map, which has offset vectors that represent a displacement of pixels of the digital image to different locations for performing the image editing operation. Pixel values of the digital image are copied to the image pixels affected by the operation by: determining the vectors pixels that correspond to the image pixels affected by the image editing operation and mapping the pixel values of the image pixels represented by the determined offset vectors to the affected pixels. According to this mapping, the pixel values of the affected pixels are set, effective to perform the image editing operation. 1. In a digital medium environment to perform image editing operations involving patch matching , a method implemented by a computing device , the method comprising:receiving, by the computing device, a digital image relative to which an image editing operation is to be performed;exposing, by the computing device, the digital image to a patch matcher having an offset prediction neural network; and generating, with the offset prediction neural network, an offset prediction as a displacement map, the displacement map comprising offset vectors that represent a displacement of image pixels of the digital image for performing the image editing operation;', 'determining the offset vectors that correspond to the image pixels affected by the image editing operation;', 'mapping pixel values of the image pixels that are represented by the determined offset vectors to the affected image pixels, and', 'setting pixel values of the affected image pixels according to the ...

Подробнее
Номер записи: 63
09-04-2020 дата публикации

SYSTEMS AND METHODS FOR DIGITIZED DOCUMENT IMAGE DATA SPILLAGE RECOVERY

Номер: US20200110959A1
Автор: SLATTERY Douglas
Принадлежит:

Systems and methods for digitized document image data spillage recovery are provided. One or more memories may be coupled to one or more processors, the one or more memories including instructions operable to be executed by the one or more processors. The one or more processors may be configured to capture an image; process the image through at least a first pass to generate a first contour; remove a preprinted bounding region of the first contour to retain text; generate one or more pixel blobs by applying one or more filters to smudge the text; identify the one or more pixel blobs that straddle one or more boundaries of the first contour; resize the first contour to enclose spillage of the one or more pixel blobs; overlay the text from the image within the resized contour; and apply pixel masking to the resized contour. 120-. (canceled)21. A data spillage recovery system comprising:at least one processor; and preprocess an image;', 'subject the image through a first pass to generate a first contour;', 'remove a first portion of the first contour to retain text;', 'apply one or more filters to smudge the text so as to generate one or more pixel blobs;', 'identify the one or more pixel blobs that exceed one or more boundary lines of the first contour;', 'resize the first contour to enclose spillage of the one or more pixel blobs;', 'overlay the text from the image within the resized contour; and', 'perform one or more conditional checks of the resized contour., 'at least one memory coupled to the at least one processor, the at least one memory including instructions operable to be executed by the at least one processor, the at least one processor configured to22. The data spillage recovery system of claim 21 , wherein the first pass comprises contouring the first portion based on edge detection.23. The data spillage recovery system of claim 21 , wherein removal of the first portion comprises removal of one or more horizontal and vertical lines.24. The data spillage ...

Подробнее
Номер записи: 64
09-04-2020 дата публикации

METHOD AND SYSTEM FOR LOCALIZING IMPLANTED INTRACRANIAL ELECTRODE

Номер: US20200111207A1
Автор: CHOU Chien-Chen, LEE Cheng-Chia, PENG Syu-Jyun, YU Hsiang-Yu
Принадлежит:

A method for localizing an intracranial electrode in a subject's brain is provided. The intracranial electrode has at least one electrode contact. The method includes: acquiring a first brain image reconstructed from first image data acquired after electrode-implantation; acquiring a second brain image reconstructed from second image data acquired before the electrode-implantation; co-registering the first brain image and the second brain image to acquire spatial transformation parameters; extracting a first coordinate of the electrode contact from the first brain image; converting the first coordinate into a second coordinate in the second brain image by using the spatial transformation parameters; co-registering the second brain image and a universal brain atlas to define functional zones in the second brain image; and defining a corresponding functional zone where the second coordinate is located. Another alternative method and a system for localizing an intracranial electrode are also provided herein. 1. A method for localizing an intracranial electrode in a brain of a subject , the method comprising:acquiring a first brain image reconstructed from first image data acquired after implantation of the intracranial electrode, wherein the intracranial electrode has at least one electrode contact;acquiring a second brain image reconstructed from second image data acquired before the implantation of the intracranial electrode;co-registering the first brain image and the second brain image to acquire spatial transformation parameters;extracting a first coordinate of the electrode contact from the first brain image;converting the first coordinate into a second coordinate in the second brain image by using the spatial transformation parameters;co-registering the second brain image and a universal brain atlas to define functional zones in the second brain image; anddefining a corresponding functional zone where the second coordinate is located.2. The method of claim 1 , ...

Подробнее
Номер записи: 65
09-04-2020 дата публикации

Systems and methods for enhancing vision

Номер: US20200111240A1
Автор: Amitabha Gupta
Принадлежит: Individual

A method for enhancing a user's vision is disclosed. The method includes: obtaining a first image corresponding to a left viewpoint of a scene and a second image corresponding to a right viewpoint of the scene; identifying a first central region of the first image corresponding to a central visual field of the user's left eye and a second central region of the second image corresponding to a central visual field of the user's right eye; applying a first image transformation to one of the first central region and a first peripheral region surrounding the first central region to obtain a first transformed image, wherein applying the first image transformation to a region of an image includes: detecting contours of objects in the region; generating graphical indications of the detected contours of the objects; and modifying the image to include the graphical indications; applying the first image transformation to one of the second central region and a second peripheral region surrounding the second central region to obtain a transformed second image; combining the transformed first and second images to obtain a third image; displaying the third image on a near-eye display.

Подробнее
Номер записи: 66
13-05-2021 дата публикации

ORGAN ISOLATION IN SCAN DATA

Номер: US20210142471A1
Автор: Samaniego Raymond, Tran Tuan T.
Принадлежит:

A method for analyzing scan data. In some embodiments, the method includes forming, from a first scan data array, a first mask, each element of the first mask being one or zero according to whether the corresponding element of the first scan data array exceeds a first threshold; forming, from the first scan data array, a second mask, each element of the second mask having a value of one or zero according to whether the corresponding element of the first scan data array exceeds a second threshold, the second threshold being less than the first threshold; and forming a fourth mask, the fourth mask being the element-wise product of the second mask and a third mask, the third mask being based on the first mask. 1. A method for analyzing scan data , the method comprising:forming, from a first scan data array based on raw scan data, a first mask, each element of the first mask being one or zero according to whether the corresponding element of the first scan data array exceeds a first threshold;forming, from the first scan data array, a second mask, each element of the second mask having a value of one or zero according to whether the corresponding element of the first scan data array exceeds a second threshold, the second threshold being less than the first threshold; andforming a fourth mask, the fourth mask being the element-wise product of the second mask and a third mask, the third mask being based on the first mask.2. The method of claim 1 , wherein:the third mask is a three dimensional array based on a fifth mask;the fifth mask is a three dimensional array based on the first mask, one, when any of the corresponding elements of the plurality of slices of the fifth mask has a value of one; and', 'zero, otherwise., 'the forming of the third mask comprises forming a slice of the third mask from a plurality of slices of the fifth mask, each element of the slice of the third mask having a value of3. The method of claim 2 , wherein the fifth mask is based on a sixth mask ...

Подробнее
Номер записи: 67
16-04-2020 дата публикации

MEDICAL IMAGE PROCESSING APPARATUS, CONTROL METHOD FOR THE SAME, AND PROGRAM

Номер: US20200118671A1
Автор: Imasugi Yusuke, Sakamoto Tsuyoshi
Принадлежит:

A plurality of analysis functions each corresponding to an organ are managed, and organ information is stored in such a manner as to correlate with a corresponding type of analysis function. The organ information indicates which of a plurality of regions included in the organ is to be subjected to thinning. Specification of one of the analysis functions is received from a user, and medical image data is acquired. A plurality of regions of an organ included in the acquired medical image data are identified. The identified plurality of regions of the organ, a region to be subjected to thinning is determined on the basis of the stored organ information and the received type of the analysis function. Thinning is performed on the determined region of the organ. An image of the thinned region is displayed together with an image of a region not subjected to thinning. 1. A medical image processing apparatus comprising:acquiring means for acquiring medical image data;determining means for determining which of a plurality of tubular structures is to be subjected to thinning in the medical image data; anddisplay control means for performing control in such a manner that a display is different between an image of a tubular structure to be subjected to thinning and an image of a tubular structure not subjected to thinning.2. The medical image processing apparatus according to claim 1 , wherein the display control means performs control in such a manner that the plurality of tubular structures is displayed in a color indicated based on color information for each of the plurality of tubular structures claim 1 , the color information being used for display.3. The medical image processing apparatus according to claim 1 , wherein the display control means performs control in such a manner that either one of the image of the tubular structure to be subjected to thinning and the image of the tubular structure not subjected to thinning determined by the determining means is displayed.4. ...

Подробнее
Номер записи: 68
10-05-2018 дата публикации

SYSTEM ON CHIP AND METHOD FOR DATA PROCESSING

Номер: US20180129901A1
Автор: Jo Seok-hwan, Kim Do-Hyung
Принадлежит:

An electronic apparatus is disclosed. The electronic apparatus includes a plurality of digital signal processors and a prediction processor configured to predict a complexity of each of a plurality of operations to be processed in the plurality of digital signal processors and to distribute the plurality of operations to the plurality of digital signal processors based on the predicted complexities. 1. A system-on-chip comprising:a plurality of digital signal processors; anda prediction processor comprising processing circuitry configured to predict a complexity of each of a plurality of operations to be processed in the plurality of digital signal processors and to distribute the plurality of operations to the plurality of digital signal processors based on the predicted complexities.2. The system-on-chip of claim 1 , wherein the prediction processor is configured to obtain a plurality of pieces of property information with respect to each of the plurality of operations claim 1 , and to predict the complexity of each of the plurality of operations using a classifier comprising circuitry configured to receive the plurality of pieces of obtained property information as input values and to output one of a plurality of complexity values as a complexity.3. The system-on-chip of claim 2 , wherein the classifier is configured to receive operation environment information of the system-on-chip as an input value.4. The system-on-chip of claim 2 , wherein the classifier comprises a support vector machine (SVM) or a deep neural network (DNN) configured to learn complexities of the plurality of pieces of property information and operation environment information.5. The system-on-chip of claim 2 , wherein the classifier includes an internal coefficient value configured to be updated by update information transmitted from an external apparatus.6. The system-on-chip of claim 2 , wherein the classifier is configured to determinea calculation result value for prediction of the ...

Подробнее
Номер записи: 69
11-05-2017 дата публикации

SYSTEMS, METHODS AND TECHNIQUES FOR INPUTTING TEXT INTO MOBILE DEVICES USING A CAMERA-BASED KEYBOARD

Номер: US20170131760A1
Автор: Li Qun, Lu Sanglu, Xie Lei, YIN Yafeng
Принадлежит:

Systems, methods and techniques are provided for interacting with mobile devices using a camera-based keyboard. The system comprises a processor system including at last one processor. The processor system is configured to at least capture a plurality of images in connection with the keyboard and at least one hand typing on the keyboard via the camera. Based on the plurality of captured images, the processor system is further configured to locate the keyboard, extract at least a portion of the keys on the keyboard, extract a hand, and detect a fingertip of the extracted hand. After that, a keystroke may be detected and localized through tracking the detected fingertip in at least one of the plurality of captured images, and a character corresponding to the localized keystroke may be determined. 1. An input system allowing a user to interact with a mobile device via a keyboard including a plurality of keys , comprising:a processor system including at last one processor, the processor system being configured to at least:capture a plurality of images in connection with the keyboard and at least one hand typing on the keyboard via a camera,locate the keyboard based on at least one of the plurality of captured images;extract at least a portion of the keys on the keyboard based on at least one of the plurality of captured images;extract a hand based on at least one of the plurality of captured images;detect a fingertip of the extracted hand based on at least one of the plurality of captured images;detect and localize a keystroke through tracking the detected fingertip based on at least one of the plurality of captured images; anddetermine a character corresponding to the localized keystroke.2. The input system according to claim 1 , wherein the interaction between the user and the mobile device is inputting text into the mobile device.3. The input system according to claim 1 , wherein the keyboard is printed on a piece of panel.4. The input system according to claim 3 , ...

Подробнее
Номер записи: 70
11-05-2017 дата публикации

IMAGE INPAINTING SYSTEM AND METHOD FOR USING THE SAME

Номер: US20170132764A1
Автор: CHAN SHENG-WEI, Lin Che-Tsung
Принадлежит:

An image inpainting method includes the following steps: segmenting image, acquiring a plurality of images, and having the plurality of images segment into noise-contained pixel images and non-noise-contained pixel images, and confirming the positions of every noise pixel of the noise pixel image; and performing inpainting in light of the noise-contained pixel images, finding out the offset map and geometric relationship of the pixel corresponding relationship without being subjected to the affection of noise and having the pixel corresponding relationship with minimum parallax, making use of the offset map or the geometric relationship to extract corresponding pixel that is not subjected to the affection of noise, performing inpainting and substituting the noise pixel in the plurality of images to generate at least a synthetic image without containing noise. 1. An image inpainting system , comprising:a camera module for acquiring a plurality of images; andan inpainting module coupled to the camera module for receiving the plurality of images from the camera module and having the plurality of images perform a noise detection where the plurality of images are segmented into noise-contained pixel images and non-noise-contained pixel images, confirming the positions of every noise pixel of the noise pixel images, finding out the offset map and geometric relationship of the pixel corresponding relationship without being subjected to the affection of noise and having the pixel corresponding relationship with minimum parallax, making use of the offset map or the geometric relationship to extract corresponding pixel that is not subjected to the affection of noise, performing inpainting and substituting the noise pixel in the plurality of images to generate at least a synthetic image without containing noise.2. The image inpainting system as claimed in claim 1 , wherein the camera module possesses at least two camera units that are arranged in array mode.3. The image ...

Подробнее
Номер записи: 71
07-08-2014 дата публикации

Method for determining markings in relief on the outer surface of the sidewall of a tyre

Номер: US20140219541A1
Автор: Alexandre Joly, Guillaume Noyel, Jean-Paul Zanella
Принадлежит: Compagnie Generale des Etablissements Michelin SCA, Michelin Recherche et Technique SA France

A method of determining relief markings on a tyre's sidewall surface includes assigning, to each pixel of a three-dimensional image of the surface, a grey-level value proportional to an elevation point corresponding to the pixel, to obtain a starting image. Using linear structuring elements of successively increasing sizes and oriented circumferentially, a series of successive morphological openings is performed iteratively on the starting surface. An image value obtained after a morphological opening using a structuring element is subtracted from an image value obtained after a morphological opening using a structuring element of an immediately lower size, to obtain a succession of images flattened by differencing. A thresholding operation is performed on the images flattened by differencing, to obtain binary images. A set-theoretic union of values of each of the binary images is performed, to obtain a final binary image in which markings appear in relief.

Подробнее
Номер записи: 72
03-06-2021 дата публикации

Semantic Segmentation Architecture

Номер: US20210166347A1
Автор: Arani Elahe, Marzban Shabbir, Pata Andrei, Zonooz Bahram
Принадлежит:

A semantic segmentation architecture comprising an asymmetric encoder-decoder structure, wherein the architecture comprises further an adapter for linking different stages of the encoder and the decoder. The adapter amalgamates information from both the encoder and the decoder for preserving and refining information between multiple levels of the encoder and decoder. In this way the adapter aggregates features from different levels and intermediates between encoder and decoder. 1. A semantic segmentation architecture comprising an asymmetric encoder-decoder structure , wherein the asymmetric architecture comprises an adapter for linking different stages of the encoder and the decoder.2. The semantic segmentation architecture of claim 1 , wherein the adapter amalgamates information from both the encoder and the decoder for preserving and refining information between multiple levels of the encoder and decoder claim 1 , representing different levels of abstraction.3. The semantic segmentation architecture of claim 1 , wherein the adapter aggregates features from three different levels and intermediates between encoder and decoder.5. A method of progressive resizing as used in segmentation to reduce training time claim 1 , wherein the training starts with reduced image sizes followed by a progressive increase of said sizes until a final stage of training is conducted using the original image sizes claim 1 , applying label relaxation of borders in the images claim 1 , wherein first one-hot labels are created from a label map followed by a max-pool operation with stride 1.6. The method according to claim 5 , wherein each one-hot label channel is dilated so as to transform said one-hot label channel into multi-hot labels along the borders which are used to find union of labels along border pixels. This application claims priority to Netherlands Patent Application No. 2024344, titled “A Semantic Segmentation Architecture”, filed on Nov. 29, 2019, and Netherlands Patent ...

Подробнее
Номер записи: 73
08-09-2022 дата публикации

IMAGE PROCESSING APPARATUS AND OPERATION METHOD THEREOF

Номер: US20220284555A1
Автор: AHN Iljun, LEE Tammy, PARK Jaeyeon, SHIN Hanul, SONG Youngchan
Принадлежит: SAMSUNG ELECTRONICS CO., LTD.

An image processing apparatus, including a memory configured to store one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to obtain similarity information indicating a similarity between each pixel of a plurality of pixels included in a first image and an adjacent pixel of the each pixel; generate a weight map including weight information corresponding to the each pixel, based on the similarity information; generate a spatially variant kernel including a plurality of kernels corresponding to the plurality of pixels, based on the weight map and a spatial kernel including weight information based on a location relationship between the each pixel and the adjacent pixel; and generate a second image by applying the spatially variant kernel to the first image. 1. An image processing apparatus comprising:a memory configured to store one or more instructions; and obtain similarity information indicating a similarity between each pixel of a plurality of pixels included in a first image and an adjacent pixel of the each pixel;', 'generate a weight map including weight information corresponding to the each pixel, based on the similarity information;', 'generate a spatially variant kernel including a plurality of kernels corresponding to the plurality of pixels, based on the weight map and a spatial kernel including weight information based on a location relationship between the each pixel and the adjacent pixel; and', 'generate a second image by applying the spatially variant kernel to the first image., 'a processor configured to execute the one or more instructions stored in the memory to2. The image processing apparatus of claim 1 , wherein the processor is further configured to execute the one or more instructions to:obtain first similarity information, based on a difference between the each pixel and a first adjacent pixel at a first relative location with respect to the each pixel; andobtain second similarity ...

Подробнее
Номер записи: 74
09-05-2019 дата публикации

GENERATING ARTISTIC DESIGNS ENCODED WITH ROBUST, MACHINE-READABLE DATA

Номер: US20190139176A1
Автор: Ambiel Christopher A., Kamath Ajith M., Sharma Ravi K., Stach John F.
Принадлежит:

Artwork carrying machine readable data is generated by editing artwork according to a data signal or transforming the data signal into artwork. The machine-readable data signal is generated from a digital payload and converted into an image tile. Artwork is edited according to the image tile by moving graphic elements, adapting intersections of lines, or altering line density, among other techniques. Artwork is generated from the data signal by skeletonizing it and applying morphological operators to a skeletal representation, such as a medial axis transform. Artistic effects are introduced by filtering the data signal with directional blurring or shape filters. 1. A method of generating artwork carrying a machine-readable data signal , the method comprising:obtaining artwork;generating a data signal from a digital payload, the generating comprising generating payload carrying and synchronization signal components;prioritizing the payload carrying and synchronization components by applying a weighting to the components derived from measuring robustness at different ratios of the signal components, and selecting a ratio of signal components based on the measured robustness; andediting the artwork according to the data signal to produce output artwork carrying the digital payload.2. The method of further comprising:measuring robustness of the data signal at spatial blocks within the output artwork to determine a robustness metric per spatial block;identifying areas with weak data signal from the robustness metric per spatial block; andupdating the editing of the artwork at the areas with weak data signal by inserting additional graphic elements according to the data signal.3. The method of wherein the editing comprises moving position of graphic objects according to a signal gradient of the data signal.4. The method of wherein the editing comprises editing line density of line elements by removing interior of the line element according to the data signal.5. The method ...

Подробнее
Номер записи: 75
09-05-2019 дата публикации

IMAGE DEBLURRING METHOD BASED ON LIGHT STREAK INFORMATION IN AN IMAGE

Номер: US20190139199A1
Автор: Gao Wen, WANG RONGGANG, Wang Zhenyu, Zhang Xinxin
Принадлежит:

An image deblurring method based on light streak information in an image is provided, wherein shape information of a blur kernel is obtained based on a light streak in a motion blur image and image restoration is constrained by combining the shape information, a natural image and the blur kernel to thereby obtain an accurate blur kernel and a high-quality restored image. The method specifically comprises: selecting an optimum image patch including an optimum light streak; extracting shape information of a blur kernel from the optimum image patch including the optimum light streak; performing blur kernel estimation to obtain the final blur kernel; performing non-blind deconvolution and restoring a sharp restored image as a final deblurred image. The present disclosure establishes a blurry image test set of captured images including light streaks and a method to: obtain an accurate blur kernel and a high quality restore image. 1. An image deblurring method based on light streak information in an image , wherein shape information of a blur kernel is obtained based on a light streak in a motion blur image and image restoration is constrained by combining the shape information , a natural image and the blur kernel to thereby obtain an accurate blur kernel and a high-quality restored image , comprising steps of:1) selecting an optimum image patch including an optimum light streak;2) extracting shape information of the blur kernel from the optimum image patch including the optimum light streak;3) performing blur kernel estimation by combining the shape information of the blur kernel obtained in step 2) and sparse priors to constrain the blur kernel, and iteratively computing an intermediate image and the blur kernel to obtain a final blur kernel; and4) performing non-blind deconvolution to thereby restoring a sharp restored image through a non-blind restoration algorithm as a final deblurred image.2. The image deblurring method based on light streak information in an image ...

Подробнее
Номер записи: 76
30-04-2020 дата публикации

IMAGE PROCESSING METHOD, IMAGE PROCESSING SYSTEM, AND STORAGE MEDIUM

Номер: US20200134795A1
Автор: Yang Quan, Zhang Shunhang
Принадлежит:

An image processing method, an image processing system and a storage medium are provided. The image processing method includes: acquiring an initial image; extracting a contour of a predetermined target included in the initial image during a transmission process of pixel data of the initial image; and obtaining information of the predetermined target according to the contour of the predetermined target included in the initial image. 1. An image processing method , comprising:acquiring an initial image;extracting a contour of a predetermined target comprised in the initial image during a transmission process of pixel data of the initial image; andobtaining information of the predetermined target according to the contour of the predetermined target comprised in the initial image.2. The image processing method according to claim 1 , wherein extracting the contour of the predetermined target comprised in the initial image comprises:performing an image preprocessing operation on the pixel data of the initial image sequentially acquired in the transmission process to sequentially obtain binary pixel data of a binary image corresponding to the initial image; andextracting at least one connected domain in the binary image based on the binary pixel data, which has been obtained, to determine the contour of the predetermined target comprised in the initial image.3. The image processing method according to claim 2 , wherein the image preprocessing operation comprises:sequentially performing a grayscale conversion operation on the pixel data of the initial image to obtain grayscale values of the pixel data of the initial image; andcomparing the grayscale values of the pixel data with a threshold parameter, and in a case where a grayscale value of one of the pixel data is greater than the threshold parameter, a grayscale value of a corresponding binary pixel data is zero, and in a case where a grayscale value of one of the pixel data is less than or equal to the threshold ...

Подробнее
Номер записи: 77
30-04-2020 дата публикации

CHARACTERIZATION METHOD FOR FINE-GRAINED SEDIMENTARY ROCK LAMINAR TEXTURE

Номер: US20200134805A1
Автор: He Lingxiao, Li Mingpeng, WANG GUANMIN, Xiong Zhouhai
Принадлежит:

The present application relates to a characterization method for fine-grained sedimentary rock laminar texture, including S1: image preprocessing; S2: loading the image, and normalizing the image to a specified size; S3: performing mean filtering, dilation operation and binarization processing on the image; S4: determining whether laminars are developed; S5: determining the number of bright laminars and dark laminars; S6: determining the continuity of bright laminars and dark laminars; S7: according to the statistical result and the calculation result, recording the characterized parameters into Excel. The present application can accurately characterize the texture features of fine-grained sedimentary rock laminar. Compared with the prior art, the present application have higher efficiency and satisfies the requirement of symmetrically depicting the growth features of fine-grained sedimentary rock laminar, and a technical support is provided for the exploration and development of shale oil and gas. 1. A characterization method for a fine-grained sedimentary rock laminar texture , wherein , including the following specific steps:S1: image preprocessing:acquiring a microscopic image of a fine-grained sedimentary rock thin section, and daubing non-laminar feature in the microscopic image of the fine-grained sedimentary rock thin section;S2: loading the image, and normalizing the image to a specified size;S3: performing mean filtering, dilation operation and binarization processing on the image successively;S4: determining whether laminars are developed:counting bright pixel points in each row of the image; setting a first threshold according to peaks, i.e., high values of the bright pixel points; and determining, according to the first threshold, whether laminars are developed in the image;S5: determining the number of bright laminars and dark laminars:setting a second threshold, finding the positions of troughs according to adjacent two peaks; if an elevation ...

Подробнее
Номер записи: 78
30-04-2020 дата публикации

METHODS OF HIGH-DEFINITION CELLULAR LEVEL SET IN B-SPLINES FOR MODELING AND TOPOLOGY OPTIMIZATION OF THREE-DIMENSIONAL CELLULAR STRUCTURES

Номер: US20200134918A1
Автор: Wang Michael Yu
Принадлежит:

Techniques for designing and optimization of solid/cellular structures are described using a modeling process referred to as high-definition cellular level set in B-splines (HD-CUBS). With this process, the entire design domain for the solid/cellular structure in question is subdivided into a set of connected volumetric cells in three dimensions. An implicit trivariate B-spline function is defined on each subdomain cell. With this parameterization scheme, constraints can be imposed on the relevant B-spline coefficients to naturally maintain geometric continuities at the connection faces between neighboring cells. The method offers several useful properties and powerful functionalities to build and modify a solid/cellular structure in the modeling process and to conduct topology optimization by directly adjusting the B-spline coefficients. The model construction can be carried out using a fast B-spline interpolation, and the topology optimization can involve a sequence of discrete B-spline convolutions. 1. A system comprising ,a processor; anda memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:receiving volumetric data defining a structure; and partitioning a global design domain for the structure into subdomain cells in three-dimensions;', 'defining cellular level set functions for respective subdomain cells of the subdomain cells; and', 'defining parameters of the cellular level set functions using B-spline basis functions for the respective subdomain cells., 'generating a three-dimensional model of the structure based on the volumetric data, comprising2. The system of claim 1 , wherein the generating further comprises:initializing the cellular level set functions using a fast B-spline interpolation method or a fast discrete B-spline convolution method to determine B-spline coefficients for the B-spline basis functions based on the volumetric data, resulting in initialized cellular ...

Подробнее
Номер записи: 79
10-06-2021 дата публикации

SYSTEMS AND METHODS FOR DIGITIZED DOCUMENT IMAGE DATA SPILLAGE RECOVERY

Номер: US20210174119A1
Автор: SLATTERY Douglas
Принадлежит:

Systems and methods for digitized document image data spillage recovery are provided. One or more memories may be coupled to one or more processors, the one or more memories including instructions operable to be executed by the one or more processors. The one or more processors may be configured to capture an image; process the image through at least a first pass to generate a first contour; remove a preprinted bounding region of the first contour to retain text; generate one or more pixel blobs by applying one or more filters to smudge the text; identify the one or more pixel blobs that straddle one or more boundaries of the first contour; resize the first contour to enclose spillage of the one or more pixel blobs; overlay the text from the image within the resized contour; and apply pixel masking to the resized contour. 140-. (canceled)41. A data recovery system comprising:a memory; and generate one or more pixel blobs based on application of a plurality of filters to smudge data from an image;', 'adjust a first contour of the image to enclose spillage of the one or more pixel blobs;', 'overlay the smudge data from the image within the adjusted first contour; and', 'perform one or more conditional checks of the adjusted first contour., 'a processor coupled to the memory, the processor configured to42. The data recovery system of claim 41 , wherein the processor is configured to subject the image through a plurality of passes to generate the first contour.43. The data recovery system of claim 42 , wherein a first pass from the plurality of passes identifies one or more shapes in the image.44. The data recovery system of claim 43 , wherein the processor is configured to create one or more bounding boxes to identify the one or more shapes.45. The data recovery system of claim 41 , wherein the processor is configured to create a mask to remove one or more pixels from the adjusted first contour.46. The data recovery system of claim 41 , wherein the processor is ...

Подробнее
Номер записи: 80
24-05-2018 дата публикации

CASCADED-TIME-SCALE BACKGROUND MODELING

Номер: US20180144476A1
Автор: Smith Gregory
Принадлежит:

The techniques and systems described for a cascaded-time-scale background modeling technique. In various implementations, the technique includes maintaining a short-term background model, which can be updated for every input video frame. The technique further includes maintaining a medium-term background model, which updates less frequently than the short-term background model. The medium-term background model updates using the short-term background model, where the short-term background model provides updated pixel values and/or identifies pixel locations in the medium-term background to update. The technique can also include maintaining a long-term background model, which updates less frequently than the medium-term background model. The long-term background model can be updated using a set of medium-term background models, which can indicate which areas of the background are stable and should be updated. Pixel values in these stable areas can be different from the values in the long-term background model, indicating a change to the background. 1. A method for background modeling , comprising:determining a first background model for a sequence of video frames, wherein the first background model includes values for a background pixel at each pixel location in a video frame from the sequence of video frames;periodically determining a second background model using the first background model, wherein a time interval for periodically determining the second background model includes a set of video frames from the sequence of video frames; andusing the second background model to extract background pixels from a particular video frame from the sequence of video frames.2. The method of claim 1 , further comprising:periodically determining a third background model using a set of the second background model, the set of the second background model including the second background model and one or more previous second background models, and wherein a second time interval for ...

Подробнее
Номер записи: 81
15-09-2022 дата публикации

System and Method for Image Inpainting

Номер: US20220292651A1
Автор: Cao Chenjie, Fu Yanwei
Принадлежит:

A system for image inpainting is provided, including an encoder, a decoder, and a sketch tensor space of a third-order tensor; wherein the encoder includes an improved wireframe parser and a canny detector, and a pyramid structure sub-encoder; the improved wireframe parser is used to extract line maps from an original image input to the encoder, the canny detector is used to extract edge maps from the original image, and the pyramid structure sub-encoder is used to generate the sketch tensor space based on the original image, the line maps and the edge maps; and the decoder outputs an inpainted image from the sketch tensor space. A method thereof is also provided. 1. A system for image inpainting , comprising an encoder , a decoder , and a sketch tensor space of a third-order tensor; wherein:the encoder includes an improved wireframe parser and a canny detector, and a pyramid structure sub-encoder;the improved wireframe parser is used to extract line maps from an original image input to the encoder, the canny detector is used to extract edge maps from the original image, and the pyramid structure sub-encoder is used to generate the sketch tensor space based on the original image, the line maps and the edge maps; andthe decoder outputs an inpainted image from the sketch tensor space.2. The system of claim 1 , wherein the improved wireframe parser extracts a junction set and a line set paired by junctions of the junction set.3. The system of claim 1 , wherein when lines are corrupted by a mask claim 1 , and a line segment masking (LSM) algorithm is used to infer missed line segments with a flexible wireframe parsing.4. The system of claim 3 , wherein the flexible wireframe parsing comprises learning an LSM-HAWP network by retraining holistically attracted wireframe parsing (HAWP) with irregular and object segmentation masks claim 3 , and introducing an indicator function to denote a masking probability of each line segment according to the mask as the post-processing ...

Подробнее
Номер записи: 82
15-09-2022 дата публикации

SYSTEMS AND METHODS FOR PROCESSING ELECTRONIC MEDICAL IMAGES TO DETERMINE ENHANCED ELECTRONIC MEDICAL IMAGES

Номер: US20220292682A1
Автор: Chen Longquan, GYLLENHAAL EVAN, RAUNIYAR Niraj P.
Принадлежит: BOSTON SCIENTIFIC SCIMED, INC.

Systems and methods for processing electronic images from a medical device comprise receiving a first image frame and a second image frame from a medical device, and determining a region of interest by subtracting the first image frame from the second image frame, the region of interest corresponding to a visual obstruction in the first image frame and/or second image frame. Image processing may be applied to the first image frame and/or second image frame based on a comparison between a first area of the first image frame corresponding to the region of interest and a second area of the second image frame corresponding to the region of interest, and the first image frame and/or second image frame may be provided for display to a user. 1. A method for processing electronic images from a medical device , comprising:receiving a first image frame and a second image frame from a medical device;determining a region of interest by subtracting the first image frame from the second image frame, the region of interest corresponding to a visual obstruction in the first image frame and/or second image frame;applying image processing to the first image frame and/or second image frame based on a comparison between a first area of the first image frame corresponding to the region of interest and a second area of the second image frame corresponding to the region of interest; andproviding the first image frame and/or second image frame for display to a user.2. The method of claim 1 , wherein subtracting the first image frame from the second image frame comprises removing regions from consideration for the region of interest if the regions are similar beyond a predetermined threshold in both the first image frame and the second image frame.3. The method of claim 1 , wherein the visual obstruction comprises a reflection claim 1 , glare claim 1 , piece of debris claim 1 , and/or calculus.4. The method of claim 1 , further comprising:generating a grayscale first image frame based on ...

Подробнее
Номер записи: 83
16-05-2019 дата публикации

MAXIMUM CONNECTED DOMAIN MARKING METHOD, TARGET TRACKING METHOD, AND AUGMENTED REALITY/VIRTUAL REALITY APPARATUS

Номер: US20190147597A1
Автор: Song Zhenkun, XUE Hongzhen, Yang Quan
Принадлежит:

Embodiments of the present disclosure provide a maximum connected domain marking method, a target tracking method and an AR (Augmented Reality)/VR (Virtual Reality) apparatus, and relate to the field of image processing technology, and can obtain the maximum connected domain. A maximum connected domain marking method comprises: marking connected domains of pixels of a binary image and recording equivalent relationships; merging the equivalent connected domains according to the equivalent relationships, for pixels with the equivalent relationships in the marked results; counting the number of pixels in each merged connected domain; determining a connected domain label for the maximum connected domain according to the counted number of pixels in each connected domain; and determining coordinates of boundary pixels in the maximum connected domain based on the connected domain label. 1. A maximum connected domain marking method , comprising:marking connected domains of pixels of a binary image and recording equivalent relationships of equivalent connected domains;merging the equivalent connected domains according to the equivalent relationships, for pixels with the equivalent relationships in the marked results;counting the number of pixels in each merged connected domain;determining a connected domain label for the maximum connected domain according to the counted number of pixels in each connected domain; anddetermining coordinates of boundary pixels in the maximum connected domain based on the connected domain label.2. The method according to claim 1 , wherein determining coordinates of boundary pixels in the maximum connected domain based on the connected domain label comprises:generating row counts and column counts while sequentially reading the connected domain labels of the pixels in the binary image, and recording the coordinates of all the pixels in a first row and a last row in the maximum connected domain and the coordinates of two boundary points left and ...

Подробнее
Номер записи: 84
01-06-2017 дата публикации

METHOD AND SYSTEM FOR IDENTIFYING BLEEDING

Номер: US20170154422A1
Автор: DOWLATSHAHI Dariush, HOGAN Matthew
Принадлежит:

A method for identifying bleeding in a patient, comprising: receiving a four-dimensional data set comprising vascular voxels, each of the voxels representing a three-dimensional location of a time-varying signal; identifying the vascular voxels in the data set by comparing each time-varying signal of each voxel in the data set to a variance threshold; identifying, within the vascular voxels in the data set, blood vessel site voxels by comparing each time-varying signal of the vascular voxels to a model arterial and venous signals; generating clusters of voxels in the data set; separating the clusters of voxels into a subset of blood vessel site clusters and a subset of remaining clusters; identifying, within the subset of remaining clusters, one or more clusters that are spatially growing over time to determine one or more active bleed sites in the patient; and generating an alert if one or more active bleed sites are determined. 1. A method for identifying bleeding in a patient , the method comprising:receiving a four-dimensional data set comprising unidentified vascular voxels and unidentified non-vascular voxels, the vascular voxels comprising unidentified blood vessel site voxels and unidentified bleeding site voxels, each of the voxels representing a three-dimensional location of a time-varying signal;identifying the vascular voxels in the data set by comparing each time-varying signal of each voxel in the data set to a variance threshold;generating arterial and venous time concentration curve signals from a subset of the vascular voxels in the data set;identifying, within the vascular voxels in the data set, the blood vessel site voxels by comparing each time-varying signal of the vascular voxels to the identified arterial and venous time concentration curve signals;generating clusters of voxels in the data set by connecting spatially and temporally adjacent vascular voxels;separating the clusters of voxels into a subset of blood vessel site clusters ...

Подробнее
Номер записи: 85
17-06-2021 дата публикации

Method, system, and computer-readable medium for improving quality of low-light images

Номер: US20210183030A1
Автор: Chiuman HO, Zibo MENG
Принадлежит: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD

In an embodiment, a method includes receiving a low-light digital image; generating, by at least one processor, a resulting digital image by processing the low-light digital image with an encoder-decoder neural network comprising a plurality of convolutional layers classified into a downsampling stage and an upscaling stage, and a multi-scale context aggregating block configured to aggregate multi-scale context information of the low-light digital image and employed between the downsampling stage and the upscaling stage; and outputting, by the at least one processor, the resulting digital image to an output device.

Подробнее
Номер записи: 86
28-08-2014 дата публикации

System and method for removing image noise

Номер: US20140241636A1
Автор: Gaurav Malik, Rajesh Mahapatra, Raka Singh
Принадлежит: ANALOG DEVICES TECHNOLOGY

A system and method for removing noise from images are disclosed herein. An exemplary system includes an edge-detection-based adaptive filter that identifies edge pixels and non-edge pixels in an image and selects a filtering technique for at least one non-edge pixel based on a comparison of the at least one non-edge pixel to a neighboring pixel region, wherein such comparison indicates whether the at least one non-edge pixel is a result of low-light noise.

Подробнее
Номер записи: 87
09-06-2016 дата публикации

DIGITAL REFOCUSING METHOD

Номер: US20160165206A1
Автор: CHIN Jui, Huang Chao-Tsung
Принадлежит:

A digital refocusing method includes: to plurality of images corresponding to multiple views in a scene are obtained, the images include a central view image and at least one non-central view image; a pixel shift or a pixel index shift is performed to the non-central view image; a line scan along a pre-determined linear path is performed to the central view image and the non-central view images to obtain corresponding pixels of the central view image and corresponding pixels of the non-central view images; view interpolation based on the disparities defined in a disparity map is performed, target pixels corresponded to a novel view image are obtained from the corresponding pixels of the central view image and the corresponding pixels of the non-central view according to a target disparity; and a refocused novel view image is obtained by averaging and compositing the target pixels of novel views. 1. A digital refocusing method , comprising:obtaining a plurality of images corresponding to multiple views in a scene, wherein the images comprise a central view image and at least one non-central view image;obtaining a disparity map corresponding to the central view image;performing a pixel shift or a pixel index shift to the non-central view image;performing a line scan along a pre-determined linear path to the central view image and the non-central view image to obtain corresponding pixels of the central view image and corresponding pixels of the non-central view image;performing view interpolation based on disparities defined in the disparity map, obtaining target pixels from the corresponding pixels of the central view image and the corresponding pixels of the noncentral view image according to a target disparity, wherein the target pixels are corresponded to a novel view; andobtaining a refocused novel view image by averaging and compositing the target pixels from a plurality of novel views;wherein the view interpolation comprises:obtaining a temporary pixel by ...

Подробнее
Номер записи: 88
14-05-2020 дата публикации

Systems and Methods for Hybrid Depth Regularization

Номер: US20200151894A1
Автор: Chatterjee Priyam, Jain Ankit, Venkataraman Kartik
Принадлежит: FotoNation Limited

Systems and methods for hybrid depth regularization in accordance with various embodiments of the invention are disclosed. In one embodiment of the invention, a depth sensing system comprises a plurality of cameras; a processor; and a memory containing an image processing application. The image processing application may direct the processor to obtain image data for a plurality of images from multiple viewpoints, the image data comprising a reference image and at least one alternate view image; generate a raw depth map using a first depth estimation process, and a confidence map; and generate a regularized depth map. The regularized depth map may be generated by computing a secondary depth map using a second different depth estimation process; and computing a composite depth map by selecting depth estimates from the raw depth map and the secondary depth map based on the confidence map. 1. A depth sensing system , comprising:a plurality of cameras;a processor;a memory containing an image processing application; obtain image data for a plurality of images from multiple viewpoints using the plurality of cameras, wherein the image data for the plurality of images comprises a reference image and at least one alternate view image;', 'generate a raw depth map containing depth estimates for pixels within the reference image using the image data for the reference image and the image data for the at least one alternate view image using a first depth estimation process, and a confidence map describing reliability of depth estimates contained within the raw depth map; and', computing a secondary depth map containing depth estimates for pixels within the reference image using a second different depth estimation process; and', 'computing a composite depth map by selecting depth estimates from the raw depth map and the secondary depth map, where a depth estimate for a pixel in the reference image is selected from the raw depth map when the depth estimate is indicated as being ...

Подробнее
Номер записи: 89
18-06-2015 дата публикации

Image processing apparatus, image processing method, and computer-readable recording medium

Номер: US20150170335A1
Автор: Aiko Otsuka, Atsushi Itoh
Принадлежит: Individual

An image processing apparatus includes an exaggeration unit configured to perform on an original image including a hand-drawn element an exaggeration process that expands the hand-drawn element to generate an exaggerated image; and a reduction unit configured to reduce the exaggerated image to generate a reduced image of a predetermined size smaller than a size of the original image.

Подробнее
Номер записи: 90
24-06-2021 дата публикации

METHOD AND APPARATUS FOR CORRECTING DISTORTED DOCUMENT IMAGE

Номер: US20210192696A1
Автор: Han Junyu, Li Yulin, QIN Xiameng, XIE Qunyi, Zhu Shengxian
Принадлежит:

Embodiments of the present disclosure provide a method and apparatus for correcting a distorted document image, where the method for correcting a distorted document image includes: obtaining a distorted document image; and inputting the distorted document image into a correction model, and obtaining a corrected image corresponding to the distorted document image; where the correction model is a model obtained by training with a set of image samples as inputs and a corrected image corresponding to each image sample in the set of image samples as an output, and the image samples are distorted. By inputting the distorted document image to be corrected into the correction model, the corrected image corresponding to the distorted document image can be obtained through the correction model, which realizes document image correction end-to-end, improves accuracy of the document image correction, and extends application scenarios of the document image correction. 1. A method for correcting a distorted document image , comprising:obtaining a distorted document image; andinputting the distorted document image into a correction model, and obtaining a corrected image corresponding to the distorted document image; wherein the correction model is a model obtained by training with a set of image samples as inputs and a corrected image corresponding to each image sample in the set of image samples as an output, and the image samples are distorted.2. The method according to claim 1 , wherein the correction model comprises a deformation parameter prediction module and a deformation correction module connected in series; wherein the deformation parameter prediction module is a U-shaped convolutional neural network model obtained by training with the set of image samples as inputs and a deformation parameter of each pixel of each image sample comprised in the set of image samples as an output claim 1 , and the deformation correction module is a model obtained by training with the set of ...

Подробнее
Номер записи: 91
24-06-2021 дата публикации

BLADED ROTATING ASSEMBLY MITIGATION IN HIGH FRAME RATE VIDEO

Номер: US20210192702A1
Автор: NIELSON Thomas E., STEER Katharine S., VOLANTE Jackson W.
Принадлежит: BAE Systems Information and Electronic Systems Integration Inc.

The system and method of frame differencing in high frame rate video to mitigate distortion caused by a bladed rotating assembly in the high frame rate video. The system and method applies one or more thresholds and a scaling factor and use a buffer of pixel values to mitigate distortions caused by blades as they pass in front of an imager. 1. A method of frame differencing in high frame rate video , comprising:providing a plurality of high frame rate video from at least one imager, wherein high frame rate video is characterized by video with a frame rate greater than 100 Hz;determining a difference between a plurality of pixels in a current frame of the at least one imager and a plurality of pixels in an separate frame that is a number of frames previous to the current frame resulting in a plurality of differenced pixels;applying a lower threshold to the plurality of differenced pixels, wherein the lower threshold is based on a minimum frame to frame noise value for the at least one imager;categorizing the plurality of differenced pixels that remain following the application of the lower threshold as potentially detected pixels;eroding a kernel;dilating the kernel;marking the potentially detected pixels as detected pixels following the dilation step;providing a buffer comprising values provided from each set of frames, the buffer having a maximum capacity;removing the oldest value from the buffer of values if the maximum capacity would be exceeded by the addition of a new value; andadding a highest detected value from the plurality of detected pixels to the buffer after multiplying by a scaling factor.2. The method of frame differencing in high frame rate video according to claim 1 , wherein the method mitigates distortion caused by a bladed rotating assembly in the high frame rate video.3. The method of frame differencing in high frame rate video according to claim 1 , further comprising applying an upper threshold to the plurality of pixels in the current frame.4 ...

Подробнее
Номер записи: 92
16-06-2016 дата публикации

Image processing devices for suppressing color fringe, and image sensor modules and electronic devices including the same

Номер: US20160171663A1
Автор: Chang-Dae JUNG, Dong-Won JANG, Hyo-Song KIM, Jihye Kim, Rae-Hong Park
Принадлежит: SOGANG UNIVERSITY RESEARCH FOUNDATION

In an image processing device, a color transformation circuit is configured to generate a color difference based on a first image of normal exposure and a second image of under exposure. A color fringe detection circuit is configured to detect color fringe in the first image, and to generate color fringe detection information based on the detected color fringe. A weight map formation circuit is configured to generate a weight map based on the color fringe detection information and the color difference. An image fusion circuit is configured to generate a third image, in which the detected color fringe is suppressed, based on the color difference and the weight map.

Подробнее
Номер записи: 93
30-05-2019 дата публикации

SYSTEM AND METHOD FOR DRIVABLE ROAD SURFACE REPRESENTATION GENERATION USING MULTIMODAL SENSOR DATA

Номер: US20190164018A1
Автор: Chen Pengfei, WANG Panqu, ZHU Ligeng
Принадлежит:

A system and method for drivable road surface representation generation using multimodal sensor data are disclosed. A particular embodiment includes: receiving image data from an image generating device mounted on a vehicle and receiving three dimensional (3D) point cloud data from a distance measuring device mounted on the vehicle; projecting the 3D point cloud data onto the 2D image data to produce mapped image and point cloud data; performing post-processing operations on the mapped image and point cloud data; and performing a smoothing operation on the processed mapped image and point cloud data to produce a drivable road surface map or representation. 1. A system comprising:a data processor; and receive image data from an image generating device mounted on a vehicle and to receive three dimensional (3D) point cloud data from a distance measuring device mounted on the vehicle;', 'project the 3D point cloud data onto the 2D image data to produce mapped image and point cloud data;', 'perform post-processing operations on the mapped image and point cloud data; and', 'perform a smoothing operation on the processed mapped image and point cloud data to produce a drivable road surface map or representation., 'a multimodal drivable road surface detection module, executable by the data processor, the multimodal drivable road surface detection module being configured to perform a multimodal drivable road surface detection operation configured to2. The system of being configured to perform a primary filtering operation on the 3D point cloud data using a Random Sample Consensus (RANSAC) operation.3. The system of being configured to perform a secondary filtering and mapping operation on the image data and the 3D point cloud data using a density-based spatial clustering of applications with noise (DBSCAN) operation.4. The system of being configured to perform pixel dilation and post-processing operations on the mapped image and point cloud data.5. The system of being ...

Подробнее
Номер записи: 94
29-09-2022 дата публикации

SUPER-RESOLUTION RECONSTRUCTION METHOD AND APPARATUS FOR THREE-DIMENSIONAL CONTRAST-ENHANCED ULTRASOUND IMAGES

Номер: US20220309613A1
Автор: YIN Jingyi, Zhang Jue
Принадлежит: Nanjing Transcend Vivoscope Bio-Technology Co., LTD

Disclosed are a super-resolution reconstruction method and an apparatus for three-dimensional contrast-enhanced ultrasound images, a computer readable storage medium and an electronic device. The method includes: performing at least one thinning operation on a first three-dimensional local image sequence, the thinning operation being configured to enhance motion trajectories of microbubbles; and performing an image reconstruction operation based on the first three-dimensional local image sequence subjected to the at least one thinning operation, so as to generate three-dimensional super-resolution images. The super-resolution reconstruction method for the three-dimensional contrast-enhanced ultrasound images, by means of performing thinning operations (for example, respectively performing a first thinning operation and a second thinning operation) on the first three-dimensional local image sequence, highlights motion trajectories of microbubbles, thereby improving a signal-to-noise ratio of an image. Compared with a prior method, the reconstruction efficiency and precision of the three-dimensional super-resolution imaging are improved. 1. A super-resolution reconstruction method for three-dimensional contrast-enhanced ultrasound images , applied to a first three-dimensional local image sequence comprising microbubbles , comprising:performing at least one thinning operation on the first three-dimensional local image sequence, wherein the thinning operation is used to enhance motion trajectories of microbubbles; andperforming an image reconstruction operation based on the first three-dimensional local image sequence subjected to the at least one thinning operation, so as to generate a three-dimensional super-resolution image.2. The super-resolution reconstruction method for three-dimensional contrast-enhanced ultrasound images according to claim 1 , wherein the performing at least one thinning operation on the first three-dimensional local image sequence comprises: ...

Подробнее
Номер записи: 95
29-09-2022 дата публикации

METHOD AND DEVICE OF EXTRACTING LABEL IN MEDICAL IMAGE

Номер: US20220309676A1
Автор: LI Yingying
Принадлежит: BOE Technology Group Co., Ltd.

A method and a device of extracting a label in a medical image are provided. The method includes: performing an edge detection on the medical image by using an edge detection algorithm, to acquire edge information in the medical image; determining at least one target area defined by the edge information; performing a fitting process on the at least one target area, to obtain a fitting area; and extracting the label in the medical image by selecting, from the fitting areas, at least one target fitting area matching a preset condition, wherein the preset condition is set based on a characteristic of the fitting area. 1. A method of extracting a label in a medical image , comprising:performing an edge detection on the medical image by using an edge detection algorithm, to acquire edge information in the medical image;determining at least one target area defined by the edge information;acquiring, based on the medical image, a color characteristic corresponding to the edge information of the at least one target area; andsorting the at least one target area based on the color characteristic into categories, wherein different categories correspond to different lesion types in the medical image.2. The method according to claim 1 , whereinbefore performing the edge detection on the medical image by using the edge detection algorithm, the method further comprises: filtering the medical image, to obtain a filtered medical image; andthe edge detection is performed on the filtered medical image.3. The method according to claim 1 , wherein determining the at least one target area defined by the edge information comprises:dilating the at least one area defined by the edge information, and determining the dilated at least one area as the at least one target area.4. The method according to claim 1 , wherein the medical image is an eye fundus image claim 1 , and the edge detection algorithm employs two thresholds for detection.5. The method according to claim 4 , wherein the two ...

Подробнее
Номер записи: 96
21-05-2020 дата публикации

DETECTING MAGNETIC INK CHARACTER RECOGNITION CODES

Номер: US20200160080A1
Автор: Golding Paul
Принадлежит:

A method for image processing is disclosed. The method includes: obtaining an image including a check with a magnetic ink character recognition (MICR) code; generating a mask including a plurality of shapes based on the image and an estimated rotation angle of the check; generating a stroke width map (SWM) by applying a stroke width transform (SWT) to a plurality of regions in the image corresponding to the plurality of shapes; generating a first word line associated with a first region based on a plurality of words in the SWM; rotating a portion of the SWM associated with the first word line; and detecting, after rotating, the MICR code by applying a plurality of OCR processes to the portion of the SWM. 1. A method for image processing , comprising:obtaining an image comprising a check with a magnetic ink character recognition (MICR) code;generating a mask comprising a plurality of shapes based on the image and an estimated rotation angle of the check;generating a stroke width map (SWM) by applying a stroke width transform (SWT) to a plurality of regions in the image corresponding to the plurality of shapes;generating a first word line associated with a first region based on a plurality of words in the SWM;rotating a portion of the SWM associated with the first word line; anddetecting, after rotating, the MICR code by applying a plurality of OCR processes to the portion of the SWM.2. The method of claim 1 , wherein generating the mask comprises:identifying a plurality of blobs in the image;fitting a first plurality of ellipses to the plurality of blobs;calculating the estimated rotation angle of the check based on the first plurality of ellipses;generating a kernel based on the estimated rotation angle of the check;dilating the plurality of blobs based on the kernel;fitting a second plurality of ellipses to the plurality of blobs after dilating the plurality of blobs based on the kernel; andrevising the estimated rotation angle of the check based on the second ...

Подробнее
Номер записи: 97
30-05-2019 дата публикации

METHOD FOR PARALLEL DETECTION OF DISPARITIES IN A HIGH RESOLUTION VIDEO

Номер: US20190166362A1
Автор: TOMCZYK Bartosz
Принадлежит:

A computer-implemented method for parallel detection of disparities in video from multiple customer devices under test in a system unit that comprises a central processing unit and is connected to a graphics card with a graphics processing unit, the method comprising: receiving a video signal from each of the devices under test; processing each of the received video signals in a dedicated CPU thread controlled by the CPU and a dedicated GPU thread controlled by the graphics processing unit; wherein within the CPU thread successive threads are uploaded to a memory for the graphics processing unit and the GPU thread is executed to process the frame, and the processed frames are collected from the memory for the graphics processing unit to check within the CPU thread whether disparities have occurred in the processed frame; wherein all the CPU threads are controlled by a main thread controlled by the CPU. 1131139210211240241. A computer-implemented method for parallel detection of disparities in video from multiple customer devices under test (-) in a system unit () that comprises a central processing unit () and is connected to a graphics card () with a graphics processing unit () , the method comprising:{'b': 131', '139, 'receiving a video signal from each of the devices under test (-);'}{'b': 521', '522', '211', '531', '532', '241, 'processing each of the received video signals in a dedicated CPU thread (, ) controlled by the central processing unit () and a dedicated GPU thread (, ) controlled by the graphics processing unit ();'}{'b': 521', '522', '244', '241', '531', '532', '632', '244', '241', '521', '522, 'wherein within the CPU thread (, ) successive threads are uploaded to a memory () for the graphics processing unit () and the GPU thread (, ) is executed to process () the frame, and the processed frames are collected from the memory () for the graphics processing unit () to check within the CPU thread (, ) whether disparities have occurred in the processed ...

Подробнее
Номер записи: 98
25-06-2015 дата публикации

Image processing apparatus, method, and storage medium

Номер: US20150181077A1
Автор: Koya Shimamura, Reiji Misawa
Принадлежит: Canon Inc

A binary image of an input image is generated, and a character region within the binary image and a region surrounding each character are acquired as character segmentation rectangle information. A thinning process is executed on a region within the binary image which is identified based on the character segmentation rectangle information to acquire a thinned image. An edge detected image of the region identified based on the character segmentation rectangle information is acquired. Whether each character identified based on the character segmentation rectangle information is a character to be separated from a background by the binarization process or not is determined based on a result of a logical AND of the thinned image and the edge detected image.

Подробнее
Номер записи: 99
22-06-2017 дата публикации

MORPHOLOGICAL AND GEOMETRIC EDGE FILTERS FOR EDGE ENHANCEMENT IN DEPTH IMAGES

Номер: US20170178305A1
Автор: Bronstein Alex, Bronstein Michael, Kimmel Ron, Manashe Ohad, Silver David H., Sperling Erez, Surazhsky Vitaly, Zabatani Aviad
Принадлежит: Intel Corporation

A mechanism is described for facilitating three-dimensional (3D) depth imaging systems, and morphological and geometric filters for edge enhancement in depth images at computing devices according to one embodiment. A method of embodiments, as described herein, includes detecting an input digital image of an object, the digital image comprising data pixels contaminated by noise and confidence values corresponding to the data pixels, and computing a morphological filter by matching the confidence pixels in the input digital image with a set of matching templates, and using a set of masking templates to determine the data pixels and confidence pixels in the filtered image. The method further include computing an edge filter by performing computation of distances between the data pixels along a plurality of directions to determine an edge direction, and determining the data pixels and and the confidence pixels in a filtered image based on the edge direction. The method may further include applying at least one of the morphological filter and the edge filter to filter the digital image. 1. An apparatus comprising:detection/reception logic to detect an input digital image of an object, the digital image comprising data pixels contaminated by noise and confidence pixels corresponding to the data pixels;morphological filter logic of filter computation engine to compute a morphological filter by matching the confidence pixels in the input digital image with a set of matching templates, and using a set of masking templates to determine the data pixels and confidence pixels in the filtered image;edge filter logic of the filter computation engine to compute an edge filter by performing computation of distances between the data pixels along a plurality of directions to determine an edge direction, and determining the data pixels and and the confidence pixels in a filtered image based on the edge direction; andapplication/execution logic to apply at least one of the morphological ...

Подробнее
Номер записи: 100