SYSTEMS AND METHODS FOR DIGITAL IMAGE ANALYSIS

Systems and methods for implementing a hierarchical image recognition framework for classifying digital images are provided. The provided hierarchical image recognition framework utilizes a multi-layer approach to model training and image classification tasks. A first layer of the hierarchical image recognition framework generates first layer confidence scores, which are utilized by the second layer to produce a final recognition score. The provided hierarchical image recognition framework permits model training and image classification tasks to be performed more accurately and in a less resource intensive fashion than conventional single-layer image recognition frameworks. In some embodiments real-time operator guidance is provided for an image classification task. 1. A computer-implemented feature extraction method for classifying pixels of a digitized pathology image , the method comprising:generating a plurality of characterized pixels from a digitized pathology image;determining in a first layer feature analysis a plurality of first layer confidence scores based on the plurality of characterized pixels, wherein the confidence scores represent a first likelihood of each pixel belonging to a specific classification;determining in a second layer feature analysis a plurality of final recognition scores based on the plurality of characterized pixels and the plurality of first layer confidence scores, wherein the recognition scores represent a final likelihood of each pixel belonging to a specific classification; andclassifying part or all of the digitized pathology image based on the final recognition scores.2. The method of claim 1 , wherein classifying part or all of the digitized pathology image further comprises:generating an image classification confidence map representing the final image classification likelihood based on the plurality of final recognition scores; andclassifying part or all of the digitized pathology image based on the image classification ...

SYSTEMS AND METHODS FOR SEGMENTING DIGITAL IMAGES

Methods and systems disclosed herein provide the capability to automatically process digital pathology images quickly and accurately. According to one embodiment, an digital pathology image segmentation task may be divided into at least two parts. An image segmentation task may be carried out utilizing both bottom-up analysis to capture local definition of features and top-down analysis to use global information to eliminate false positives. In some embodiments, an image segmentation task is carried out using a “pseudo-bootstrapping” iterative technique to produce superior segmentation results. In some embodiments, the superior segmentation results produced by the pseudo-bootstrapping method are used as input in a second segmentation task that uses a combination of bottom-up and top-down analysis. 1. A computer-implemented segmentation method for segmenting a digitized pathology image of tissue into at least two non-overlapping_regions for use in disease diagnosis , the method comprising:generating a first initial data set comprising a segmentation of pixels in the digitized pathology image as belonging to a first region using a first method of processing;generating a second initial data set comprising a current best segmentation of pixels in the digitized pathology image as belonging to the first region using a second method of processing;iteratively determining a final first region data set based on the first and second initial data sets, wherein the final first region data set comprises a segmentation of pixels in the digitized pathology image as belonging to the first region; andsegmenting the digitized pathology image into a first region and a remainder region based on the final first region data set.2. The method of claim 1 , wherein the first method of processing comprises the steps of:performing anisotropic diffusion on the digitized pathology image;performing binary thresholding on results of the anisotropic diffusion step; andperforming connected-component ...

Digital image analysis using multi-step analysis

Systems and methods for implementing a multi-step image recognition framework for classifying digital images are provided. The provided multi-step image recognition framework utilizes a gradual approach to model training and image classification tasks requiring multi-dimensional ground truths. A first step of the multi-step image recognition framework differentiates a first image region from a remainder image region. Each subsequent step operates on a remainder image region from the previous step. The provided multi-step image recognition framework permits model training and image classification tasks to be performed more accurately and in a less resource intensive fashion than conventional single-step image recognition frameworks.

Learning device, learning method, identification device, identification method, and program

Provided is a learning device including: an acquisition section that acquires a plurality of image pairs in which the same subjects appear and a plurality of image pairs in which different subjects appear; a setting section that sets feature points on one image and the other image of each image pair; a selection section that selects a plurality of prescribed feature points, which are set at the same positions of the one image and the other image, so as to thereby select a feature extraction filter for each prescribed feature point; an extraction section that extracts the features of the prescribed feature points of each of the one image and the other image by using the plurality of feature extraction filters; a calculation section that calculates a correlation between the features; and a learning section that learns a same-subject classifier on the basis of the correlation and label information.

Digital image analysis utilizing multiple human labels

Systems and methods for implementing a multi-label image recognition framework for classifying digital images are provided. The provided multi-label image recognition framework utilizes an iterative, multiple analysis path approach to model training and image classification tasks. A first iteration of the multi-label image recognition framework generates confidence maps for each label, which are shared by the multiple analysis paths to update the confidence maps in subsequent iterations. The provided multi-label image recognition framework permits model training and image classification tasks to be performed more accurately than conventional single-label image recognition frameworks.

LEARNING DEVICE, LEARNING METHOD, AND PROGRAM

Disclosed is a learning device. A feature-quantity calculation unit extracts a feature quantity from each feature point of a learning image. An acquisition unit acquires a classifier already obtained by learning as a transfer classifier. A classifier generation unit substitutes feature quantities into weak classifiers constituting the transfer classifier, calculates error rates of the weak classifiers on the basis of classification results of the weak classifiers and a weight of the learning image, and iterates a process of selecting a weak classifier of which the error rate is minimized a plurality of times. In addition, the classifier generation unit generates a classifier for detecting a detection target by linearly coupling a plurality of selected weak classifiers. 1. A learning device comprising:a feature-quantity extraction unit for extracting a feature quantity from a feature point of a learning image with respect to each of a plurality of learning images including a learning image including a detection target and a learning image not including the detection target;a weak-classification calculation unit for calculating a classification result of the detection target according to a weak classifier for every learning image by substituting the feature quantity corresponding to the weak classifier into the weak classifier with respect to each of a plurality of weak classifiers constituting a transfer classifier, which is a classifier for detecting the detection target obtained by statistical learning; anda classifier generation unit for generating the classifier for detecting the detection target using the weak classifier selected from the plurality of weak classifiers on the basis of the classification result.2. The learning device according to claim 1 , further comprising:a weight setting unit for setting a weight of the learning image based on the classification result; andan error-rate calculation unit for calculating an error rate of the weak classifier ...

INFORMATION PROCESSING DEVICE AND METHOD, PROGRAM, AND RECORDING MEDIUM

An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points; an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation. 111-. (canceled)12. An information processing apparatus , comprising:a processor configured to compute data indicative of a position of at least one joint of a human subject; anda determination unit for determining a gesture of the human subject based on the computed data.13. The information processing apparatus of claim 12 , wherein:the information processing apparatus further comprises a pixel value extraction unit for obtaining values of pixels corresponding to positions of one or more sample points within an image of a human subject; andthe processor is further configured to compute the data based on the obtained pixel values, the data being indicative of a match between a corresponding one of the sample point positions and a position of a predetermined joint of the human subject.14. The information processing apparatus of claim 13 , wherein the extraction unit is configured to extract the image of the human subject from a picked-up image.15. The information processing apparatus of claim 14 , further comprising an outline extraction unit for extracting an outline of the human subject from the picked-up image.16. The information processing ...

IMAGE PROCESSING DEVICE, METHOD THEREOF, AND PROGRAM

An image processing device includes a difference image generation unit which generates a difference image by obtaining a difference between frames of a cutout image which is obtained by cutting out a predetermined region on a photographed image; a feature amount extracting unit which extracts a feature amount from the difference image; and a recognition unit which recognizes a specific movement of an object on the photographed image based on the feature amount which is obtained from the plurality of difference images which are aligned in time sequence. 1. An image processing device comprising:a difference image generation unit which generates a difference image by obtaining a difference between frames of a cutout image which is obtained by cutting out a predetermined region on a photographed image;a feature amount extracting unit which extracts a feature amount from the difference image; anda recognition unit which recognizes a specific movement of an object on the photographed image based on the feature amount which is obtained from the plurality of difference images which are aligned in time sequence.2. The image processing device according to claim 1 ,wherein the recognition unit recognizes a gesture by a user's hand as a specific movement of the object.3. The image processing device according to claim 2 , further comprising:a hand detection unit which detects the user's hand from the photographed image; anda cutout region determination unit which determines the predetermined region based on a position of the detected user's hand on the photographed image.4. The image processing device according to claim 3 ,wherein the cutout region determination unit determines the predetermined region based on the position of the user's hand when the detected user's hand is located in a certain range on the photographed image with respect to the photographed image of a continuous plurality of frames.5. The image processing device according to claim 2 , further comprising:a ...

INTEGRATED INTERACTIVE SEGMENTATION WITH SPATIAL CONSTRAINT FOR DIGITAL IMAGE ANALYSIS

An integrated interactive segmentation with spatial constraint method utilizes a combination of several of the most popular online learning algorithms into one and implements a spatial constraint which defines a valid mask local to the user's given marks. Additionally, both supervised learning and statistical analysis are integrated, which are able to compensate each other. Once prediction and activation are obtained, pixel-wised multiplication is conducted to fully indicate how likely each pixel belongs to the foreground or background. 1. A method of image processing programmed in a memory of a device comprising:a. utilizing user input to generate a learned model for prediction;b. utilizing statistical analysis for activation;c. defining a local mask from the user input, wherein the local mask limits the image processing to a local area; andd. performing object segmentation using a combination of the prediction and the activation.2. The method of further comprising receiving input from a user.3. The method of wherein the input comprises the user marking a foreground and a background.4. The method of further comprising combining the prediction and the activation using pixel-wise multiplication.5. The method of further comprising generating a cost function from the prediction and the activation.6. The method of wherein the cost function is optimized by graph cuts.7. The method of wherein the cost function utilizes edge detection information.8. The method of wherein object segmentation is to distinguish a foreground and a background of an image.9. The method of further comprising repeating steps a-d until a user is satisfied with a result of the image processing.10. The method of wherein the user input for defining the local mask comprises an enclosed area.11. The method of wherein the device comprises a personal computer claim 1 , a laptop computer claim 1 , a computer workstation claim 1 , a server claim 1 , a mainframe computer claim 1 , a handheld computer claim 1 ...

INFORMATION PROCESSING UNIT, INFORMATION PROCESSING METHOD, AND PROGRAM

An information processing unit includes: a diagnostic image input section that inputs the diagnostic image; an operation information obtaining section that obtains display operation history information representing an operation history of a user who controls displaying of the diagnostic image; a query image generation section that extracts a predetermined region of the input diagnostic image to generate a query image; a diagnosed image obtaining section that supplies the generated query image and the display operation history information to a diagnosed image search unit and obtains the diagnosed image obtained as a search result by the diagnosed image search unit; and a display control section that displays the diagnostic image and the obtained diagnosed image for comparison. 1. An information processing unit that displays a diagnostic image serving as a diagnosis target and a diagnosed image similar to the diagnostic image for comparison , the information processing unit comprising:a diagnostic image input section that inputs the diagnostic image;an operation information obtaining section that obtains display operation history information representing an operation history of a user who controls displaying of the diagnostic image;a query image generation section that extracts a predetermined region of the input diagnostic image to generate a query image;a diagnosed image obtaining section that supplies the generated query image and the display operation history information to a diagnosed image search unit and obtains the diagnosed image obtained as a search result by the diagnosed image search unit; anda display control section that displays the diagnostic image and the obtained diagnosed image for comparison,wherein the diagnosed image search unit includesan image feature amount extraction section that extracts an image feature amount of the query image,a search section that retrieves diagnosed images each of which includes a sub-image with an image feature amount ...

INFORMATION PROCESSING APPARATUS, OPERATION CONTROL METHOD AND PROGRAM

An information processing apparatus includes circuitry that is configured to provide a user interface to control a plurality of controllable objects. The user interface is associated with a gesture recognition area that is defined by a predetermined detection area of a sensor. The gesture recognition area is divided into a plurality of gesture recognition sub-areas based on a number of the controllable objects to be controlled by the user interface. The circuitry is further configured to detect a predetermined gesture within the predetermined detection area, determine the gesture recognition sub-area in which the predetermined gesture is detected, and perform an operation on one of the controllable objects based on the detected predetermined gesture and the determined gesture recognition sub-area in which the predetermined gesture is detected. 1. An information processing apparatus , comprising:circuitry configured toprovide a user interface to control a plurality of controllable objects, the user interface being associated with a gesture recognition area that is defined by a predetermined detection area of a sensor, the gesture recognition area being divided into a plurality of gesture recognition sub-areas based on a number of the controllable objects to be controlled by the user interface,detect a predetermined gesture within the predetermined detection area,determine the gesture recognition sub-area in which the predetermined gesture is detected, andperform an operation on one of the controllable objects based on the detected predetermined gesture and the determined gesture recognition sub-area in which the predetermined gesture is detected.2. The information processing apparatus according to claim 1 , whereinthe one of the controllable objects is a remote controllable device which is assigned to the determined gesture recognition sub-area, andthe circuitry is further configured to perform the operation by sending a predetermined command from the information ...

CLOSE RANGE NATURAL USER INTERFACE SYSTEM AND METHOD OF OPERATION THEREOF

A natural user interface system and method of operation thereof including: a display device having a display screen and a display device camera; a mobile device having a mobile device camera, an optical axis of the mobile device camera positioned at an angle to an optical axis of the display device camera; wherein: the mobile device includes a first device pairing module for pairing the mobile device with the display device; the mobile device camera and the display device camera are for: detecting a user's hand, and determining posture and movement of the user's hand; and the display device includes a motion translation module for translating the posture and movement of the user's hand into a gesture for controlling an element of a user interface on the display screen. 1. A method of operation of a natural user interface system comprising:providing a display device having a display screen and a display device camera;providing a mobile device having a mobile device camera, an optical axis of the mobile device camera positioned at an angle to an optical axis of the display device camera;pairing the mobile device with the display device;detecting a user's hand;determining posture and movement of the user's hand; andtranslating the posture and movement of the user's hand into a gesture for controlling an element of a user interface on the display screen.2. The method as claimed in further comprising rotating a viewing angle of the mobile device camera based on an orientation of the mobile device relative to an orientation of the display device.3. The method as claimed in further comprising:detecting a user's face;determining an eyeline vector from the user's face; andrefining movement of a cursor on the display screen using the eyeline vector.4. The method as claimed in wherein detecting the user's hand includes:detecting the user's hand with the mobile device camera; anddetecting the user's hand with the display device camera.5. The method as claimed in wherein ...

NATURAL USER INTERFACE SYSTEM WITH CALIBRATION AND METHOD OF OPERATION THEREOF

A natural user interface system and method of operation thereof including: providing a display screen having a range camera connected to the display screen in a known location relative to the display screen; determining a user's pointing vector as pointing towards the display screen; determining the user's pointing vector as motionless; and initializing a cursor in the center of the display screen and simultaneously calibrating the user's pointing vector as an initial pointing vector pointing at the center of the display screen. 1. A method of operation of a natural user interface system comprising:providing a display screen having a range camera connected to the display screen in a known location relative to the display screen;determining a user's pointing vector as pointing towards the display screen;determining the user's pointing vector as motionless; andinitializing a cursor in the center of the display screen and simultaneously calibrating the user's pointing vector as an initial pointing vector pointing at the center of the display screen.2. The method as claimed in further comprising providing a processing unit connected between the display screen and the range camera.3. The method as claimed in further comprising:detecting a valid pointing hand; anddetermining the user's pointing vector from the orientation of the valid pointing hand.4. The method as claimed in wherein determining the user's pointing vector as motionless includes:setting a movement threshold value of the user's pointing vector; anddetermining movement of the user's pointing vector as less than the movement threshold value.5. The method as claimed in further comprising:mapping the initial pointing vector to display coordinates of the display screen;determining a second pointing vector;mapping the second pointing vector to the display coordinates; anddetermining a movement vector ΔV by determining the difference between the display coordinates of the initial pointing vector and the second ...

IMAGE PROCESSING DEVICE, METHOD AND PROGRAM FOR MOVING GESTURE RECOGNITION USING DIFFERENCE IMAGES

An image processing device includes a difference image generation unit which generates a difference image by obtaining a difference between frames of a cutout image which is obtained by cutting out a predetermined region on a photographed image; a feature amount extracting unit which extracts a feature amount from the difference image; and a recognition unit which recognizes a specific movement of an object on the photographed image based on the feature amount which is obtained from the plurality of difference images which are aligned in time sequence. 1. An image processing device comprising:a region setting unit configured to detect a part of a body or a body as a target for being recognized from a photographed image which is aligned in time sequence and set a recognition region based on the detected part of the body or the body;a processing unit configured to track the recognition region in the photographed image set by the region setting unit;a feature amount extracting unit configured to extract a feature amount from the tracked recognition region in the photographed image;a recognition unit configured to recognize a specific movement of the part of the body or the body based on the feature amount extracted at the feature amount extracting unit; anda display control unit configured to control a display of a frame denoting the recognition region set by the region setting unit.2. The image processing device according to claim 1 , wherein the recognition unit is further configured to recognize a gesture based on the feature amount extracted by the feature amount extracting unit.3. The image processing device according to claim 1 , further comprising:a cutout region determination unit which determines a plurality of predetermined regions based on the tracked recognition region in the photographed image.4. The image processing device according to claim 3 , wherein the cutout region determination unit determines the plurality of predetermined regions based on the ...

APPARATUS AND METHOD FOR INFORMATION PROCESSING

Provided is an information processing apparatus including a sorting unit configured to sort a second data set as evaluation data with a sorter generated by learning through supervised learning that uses a first data set as teacher data, an input unit configured to receive label correction for the second data set in accordance with a sorting result from the sorting unit, and an update unit configured to update the second data set to reflect the correction received by the input unit. 1. An information processing apparatus comprising:a sorting unit configured to sort a second data set as evaluation data with a sorter generated by learning through supervised learning that uses a first data set as teacher data;an input unit configured to receive label correction for the second data set in accordance with a sorting result from the sorting unit; andan update unit configured to update the second data set to reflect the correction received by the input unit.2. The information processing apparatus according to claim 1 , whereinthe first data set and the second data set are sets of sorting objects to which labels are set,the sorting unit sorts the sorting objects and predicts corresponding labels, andthe input unit receives correction of a label set for at least one of the sorting objects when the label set for the at least one of the sorting objects is different from the label predicted by the sorting unit.3. The information processing apparatus according to claim 2 , further comprising:an output unit configured to output information indicating the sorting object whose set label is different from the label predicted by the sorting unit.4. The information processing apparatus according to claim 2 , further comprising:an evaluation unit configured to evaluate the sorting result with a confusion matrix that compares the labels set for the sorting objects and the labels predicted by the sorting unit.5. The information processing apparatus according to claim 1 , further comprising ...

LEARNING DEVICE AND METHOD, RECOGNITION DEVICE AND METHOD, AND PROGRAM

A learning device includes: a generating unit configured to generate an image having different resolution from an input image; an extracting unit configured to extract a feature point serving as a processing object from an image generated by the generating unit; a calculating unit configured to calculate the feature amount of the feature point by subjecting the feature point to filter processing employing a predetermined filter; and an identifier generating unit configured to generate an identifier for detecting a predetermined target object from the image by statistical learning employing the feature amount; with the filter including a plurality of regions, and the calculating unit taking the difference value of difference within the regions as the feature amount. 1. A learning device comprising:generating means configured to generate an image having different resolution from an input image;extracting means configured to extract a feature point serving as a processing object from an image generated by the generating means;calculating means configured to calculate the feature amount of the feature point by subjecting the feature point to filter processing employing a predetermined filter; andidentifier generating means configured to generate an identifier for detecting a predetermined target object from the image by statistical learning employing the feature amount;wherein the filter includes a plurality of regions, and the calculating means take the difference value of difference within the regions as the feature amount.2. The learning device according to claim 1 , wherein the regions of the predetermined filter have a rectangular shape.3. The learning device according to claim 1 , wherein the calculating means execute convolution operation in a differential function of a predetermined order of a Gaussian function in an arbitrary angle to calculate the summation of the absolute values of the operation results.4. The learning device according to claim 1 , wherein ...

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND PROGRAM

[Object] To provide a system that is capable of increasing the number of users using recognition processing. [Solution] An information processing device includes: a storage unit that stores learning information acquired by machine learning; an input unit that acquires identification information; and a processing unit that performs recognition processing using the learning information that is specified by the storage unit on a basis of the identification information. An information processing method is executed by a processor, the information processing method includes: storing learning information acquired by machine learning; acquiring identification information; and performing recognition processing using the learning information that is specified from storage on a basis of the identification information. A program causes a computer to achieve: a storing function for storing learning information acquired by machine learning; an input function for acquiring identification information; and a processing function for performing recognition processing using the learning information that is specified from storage on a basis of the identification information. 1. An information processing device comprising:a storage unit that stores learning information acquired by machine learning;an input unit that acquires identification information; anda processing unit that performs recognition processing using the learning information that is specified by the storage unit on a basis of the identification information.2. The information processing device according to claim 1 , whereinthe recognition processing includes recognition processing in accordance with a neural network, andthe learning information includes coefficient information of the neural network.3. The information processing device according to claim 2 , whereinthe neural network includes a neural network with a multi-layer structure.4. The information processing device according to claim 1 , whereinthe identification ...

INFORMATION PROCESSING DEVICE AND METHOD, PROGRAM AND RECORDING MEDIUM FOR IDENTIFYING A GESTURE OF A PERSON FROM CAPTURED IMAGE DATA

An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points: an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation. 1. An information processing apparatus , comprising:circuitry configured tocapture an image of a human subject;output data indicating a position of at least one joint of an upper body of the human subject, the position of the at least one joint being a place at which two parts of the human subject are joined;output, as an output result, the captured image of the human subject and the output data with a line that overlaps the captured image of the human subject and includes the position of the at least one joint of the human subject; anddetermine a posture of the human subject based on the output result.2. The information processing apparatus of claim 1 ,wherein the circuitry is configured to output the captured image of the human subject and the output result that includes the line that overlaps the captured image of the human subject and a point that indicates the position of the at least one joint of the human subject.3. The information processing apparatus of claim 1 ,wherein the circuitry is configured to capture the image of human subject without a monitoring marker being disposed on the human subject.4. The information processing apparatus ...

Information processing device, information processing method, and program

An information processing device includes a feature amount extraction unit configured to extract each feature amount from a connected image generated by connecting images photographed from different viewpoints; and a specific object recognition unit configured to perform a process of determining a position of a specific object based on the feature amount extracted by the feature amount extraction unit. The feature amount extraction unit performs a feature amount extraction process to which a separated filter in which filter-formed regions are set to be separated is applied.

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND PROGRAM

An information processing device includes a data processing unit that executes analysis of images which are captured from different viewpoints. The data processing unit executes an object distance calculation process in which pattern-irradiated images of a plurality of different viewpoints are applied, and an object detection process in which non-pattern-irradiated images are applied. 1. An information processing device , comprising:a data processing unit that executes analysis of images which are captured from different viewpoints, an object distance calculation process in which pattern-irradiated images of a plurality of different viewpoints are applied, and', 'an object detection process in which non-pattern-irradiated images are applied., 'wherein the data processing unit executes'}2. The information processing device according to claim 1 ,wherein the data processing unit generates the non-pattern-irradiated image by performing an image conversion which subtracts a pattern image from the pattern-irradiated image, and executes an object detection process in which the generated non-pattern-irradiated image is applied.3. The information processing device according to claim 1 , (a) an object distance calculation process in which pattern-irradiated images of a plurality of different viewpoints are input and the pattern-irradiated images of a plurality of different viewpoints that are input are applied, and', '(b) an object detection process in which a non-pattern-irradiated image is input and the non-pattern-irradiated image that is input is applied, and, 'wherein the data processing unit includes'}wherein the data processing unit executes the (a) and the (b) processes alternately.4. The information processing device according to claim 1 , a feature value extraction process which extracts feature values from the non-pattern-irradiated image, and', 'a specific object recognition process which executes a position determination process of a specific object based on the ...

INFORMATION PROCESSING DEVICE AND METHOD, PROGRAM AND RECORDING MEDIUM FOR IDENTIFYING A GESTURE OF A PERSON FROM CAPTURED IMAGE DATA

An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points; an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation. 1outline extraction means for extracting an outline of a subject from a picked-up image of the subject:characteristic amount extraction means for extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points;estimation means for estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction means being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; anddetermination means for determining accuracy of estimation by the estimation means using a matching cost when the estimation means carries out the estimation.. An information processing device, comprising: This application is a continuation of U.S. patent application Ser. No. 15/923,975, filed Mar. 16, 2018, which is a continuation of U.S. patent application Ser. No. 15/174,585 filed Jun. 6, 2016. (now U.S. Pat. No. 9,952,678), which is a continuation of U.S. patent application Ser. No. 13/756,977 filed Feb. 1, 2013 ...

Information processing apparatus, information processing system, program, and information processing method

[Object] To provide an information processing apparatus, an information processing system, and an information processing method that are capable of performing natural interaction between a user and a robot. [Solving Means] An information processing apparatus includes: a state-change detection unit. The state-change detection unit compares reference image information regarding an autonomously acting robot acquired at a certain time point with comparison image information regarding the autonomously acting robot acquired at another time point, and detects a state change of the autonomously acting robot on the basis of a comparison result.

IMAGE PROCESSING SYSTEM, IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND PROGRAM

An image processing system includes a storing section that stores a database in which specific pose data representing each of specific poses of a human, and effect manipulation data specifying each of manipulations applied to an image are registered in association with each other, a human region detecting section that detects a human region that is a region where a human appears in an image on which to perform image processing, a human pose recognizing section that recognizes a pose of the human in the human region detected by the human region detecting section, a matching section that finds the specific pose data matching the pose recognized by the human pose recognizing section, by referencing the database, and a manipulating section that applies a manipulation to the image on the basis of the effect manipulation data associated with the specific pose data found by the matching section. 1. An image processing system comprising:storing means for storing a database in which specific pose data representing each of specific poses of a human, and effect manipulation data specifying each of manipulations applied to an image are registered in association with each other;human region detecting means for detecting a human region that is a region where a human appears in an image on which to perform image processing;human pose recognizing means for recognizing a pose of the human in the human region detected by the human region detecting means;matching means for finding the specific pose data matching the pose recognized by the human pose recognizing means, by referencing the database stored in the storing means; andmanipulating means for applying a manipulation to the image on the basis of the effect manipulation data associated with the specific pose data found by the matching means.2. The image processing system according to claim 1 , wherein:when a plurality of humans appear in the image on which to perform image processing, the human region detecting means identifies a ...

INFORMATION PROCESSING DEVICE AND METHOD, PROGRAM AND RECORDING MEDIUM FOR IDENTIFYING A GESTURE OF A PERSON FROM CAPTURED IMAGE DATA

An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points: an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation. 1. An information processing apparatus , comprising: obtain an image of a part of a human subject, the image captured by an imaging device;', 'estimate, as an estimation result, a posture of the human subject by using a posture model image; and', 'produce output of joint position data of at least one joint of the human subject, the output representing the posture of the human subject compared with the obtained image, and an estimation accuracy determination corresponding to the estimation result., 'circuitry configured to2. The information processing apparatus of claim 1 , whereinthe posture model image is learned in advance based on sample images.3. The information processing apparatus of claim 1 , whereinthe joint position data includes position information of a coordinate of the image data, andthe position information of the coordinate indicates a two-dimensional coordinate of more than one joint of the human subject.4. The information processing apparatus of claim 1 , whereinthe joint position data includes a numerical value indicative of a likelihood of the estimation result.5. The information processing apparatus of claim 1 , wherein output ...

INFORMATION PROCESSING DEVICE AND METHOD, PROGRAM AND RECORDING MEDIUM FOR IDENTIFYING A GESTURE OF A PERSON FROM CAPTURED IMAGE DATA

An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points; an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation. 1. (canceled)2. An information processing apparatus , comprising: obtain an image of at least a part of a human subject, the image being captured by an imaging device;', 'estimate a position of a joint of the human subject based on the obtained image, the joint being a place at which two parts of the human subject are joined;', 'output, using a plurality of points indicative of the estimated position of the joint, joint position data indicative of the estimated position of the joint and estimation accuracy data indicative of an accuracy of the estimated position of the joint based on an estimation result of the position of the joint; and', 'estimate a posture of the human subject based on the output joint position data and the output estimation accuracy data., 'circuitry configured to3. The information processing apparatus of claim 2 , whereinthe estimation accuracy data is generated by a discriminator learned by a machine learning.4. The information processing apparatus of claim 3 , whereinthe discriminator is learned by Boosting.5. The information processing apparatus of claim 2 , whereinthe joint position data includes position information of a ...

IMAGE PROCESSING DEVICE, METHOD THEREOF, AND PROGRAM

An image processing device includes a difference image generation unit which generates a difference image by obtaining a difference between frames of a cutout image which is obtained by cutting out a predetermined region on a photographed image; a feature amount extracting unit which extracts a feature amount from the difference image; and a recognition unit which recognizes a specific movement of an object on the photographed image based on the feature amount which is obtained from the plurality of difference images which are aligned in time sequence. 1. An image processing device , comprising: detect one of a first part of a body as a first target to be recognized from a photographed image, wherein the photographed image is aligned in time sequence;', 'set a first region on the photographed image based on the detected first target;', 'control to overlay a first graphic based on the first region on the photographed image;', 'track the first region in the photographed image;', 'extract a first feature amount from the tracked first region in the photographed image;', 'determine a movement of the first target in the first region based on a magnitude of a change of the first feature amount; and', 'execute a first process based on the movement of the first target., 'a central processing unit (CPU) configured to2. The image processing device according to claim 1 ,wherein the CPU is further configured to:detect a second part of the body as a second target to be recognized from the photographed image, wherein the second part is different from the first part; andset a second region on the photographed image based on the second target.3. The image processing device according to claim 2 ,wherein the CPU is further configured to:generate a second graphic based on the second region; andcontrol display of the second graphic.4. The image processing device according to claim 2 ,wherein the CPU is further configured to:track the second region in the photographed image; andextract a ...

LEARNING DEVICE, LEARNING METHOD, AND PROGRAM

Disclosed is a learning device. A feature-quantity calculation unit extracts a feature quantity from each feature point of a learning image. An acquisition unit acquires a classifier already obtained by learning as a transfer classifier. A classifier generation unit substitutes feature quantities into weak classifiers constituting the transfer classifier, calculates error rates of the weak classifiers on the basis of classification results of the weak classifiers and a weight of the learning image, and iterates a process of selecting a weak classifier of which the error rate is minimized a plurality of times. In addition, the classifier generation unit generates a classifier for detecting a detection target by linearly coupling a plurality of selected weak classifiers. 1. A learning device comprising:a feature-quantity extraction unit for extracting a feature quantity from a feature point of a learning image with respect to each of a plurality of learning images including a learning image including a detection target and a learning image not including the detection target;a weak-classification calculation unit for calculating a classification result of the detection target according to a weak classifier for every learning image by substituting the feature quantity corresponding to the weak classifier into the weak classifier with respect to each of a plurality of weak classifiers constituting a transfer classifier, which is a classifier for detecting the detection target obtained by statistical learning; anda classifier generation unit for generating the classifier for detecting the detection target using the weak classifier selected from the plurality of weak classifiers on the basis of the classification result.2. The learning device according to claim 1 , further comprising:a weight setting unit for setting a weight of the learning image based on the classification result; andan error-rate calculation unit for calculating an error rate of the weak classifier ...

INFORMATION PROCESSING DEVICE, ACTION DECISION METHOD AND PROGRAM

More natural communication and interaction are enabled. The autonomous system () includes an action decision unit () that decides, based on an attention level map () in which an attention level indicating the degree of attention for each position in a predetermined space is set, the action which a drive mechanism is caused to perform. 1. An information processing device comprising: an action decision unit that decides , based on an attention level map in which an attention level indicating a degree of attention for each position in a predetermined space is set , an action which a drive mechanism is caused to perform.2. The information processing device according to claim 1 , whereinthe drive mechanism is a movement mechanism that controls at least one of a position and an attitude of an autonomous moving body, andthe action decision unit causes the drive mechanism to perform the action to control at least one of the position and the attitude of the autonomous moving body.3. The information processing device according to claim 1 , further comprising: an update unit that updates the attention level map based on information around the drive mechanism.4. The information processing device according to claim 3 , further comprising:a sensor that acquires information around the drive mechanism; anda recognition unit that performs a recognition process on sensor data acquired by the sensor, whereinthe update unit updates the attention level map based on a result of the recognition process.5. The information processing device according to claim 4 , wherein the update unit estimates claim 4 , based on the result of the recognition process claim 4 , a region where an attention level in the attention level map is made to be high or low to update the attention level map so that the attention level of the estimated region is made to be high or low.6. The information processing device according to claim 5 , wherein the update unit creates an individual attention level map in which ...

INFORMATION PROCESSING DEVICE AND METHOD, PROGRAM AND RECORDING MEDIUM FOR IDENTIFYING A GESTURE OF A PERSON FROM CAPTURED IMAGE DATA

An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points; an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation. 1. (canceled)2: An information processing apparatus , comprising: obtain, using an imaging device, an image of at least a part of a human subject; and', 'control a display to display a joint image of the at least the part of the human subject, the joint image showing a gesture of the at least the part of the human subject in accordance with the obtained image, the joint image including at least two lines joined with each other at a position corresponding to a position of at least one joint of the human subject in the joint image, the at least one joint corresponding to a place at which two parts of the human subject are joined, the two lines being not included in the obtained image obtained by the imaging device., 'circuitry configured to3: The information processing apparatus of claim 2 , wherein the circuitry is configured to control the display to display an entire image of the human subject.4: The information processing apparatus of claim 3 , wherein the entire image of the human subject is displayed with the joint image.5: The information processing apparatus of claim 3 , wherein the circuitry is configured to generate an instruction to ...

INFORMATION PROCESSING UNIT, INFORMATION PROCESSING METHOD, AND PROGRAM

An information processing unit includes: a diagnostic image input section that inputs the diagnostic image; an operation information obtaining section that obtains display operation history information representing an operation history of a user who controls displaying of the diagnostic image; a query image generation section that extracts a predetermined region of the input diagnostic image to generate a query image; a diagnosed image obtaining section that supplies the generated query image and the display operation history information to a diagnosed image search unit and obtains the diagnosed image obtained as a search result by the diagnosed image search unit; and a display control section that displays the diagnostic image and the obtained diagnosed image for comparison. 1. An information processing unit that displays a diagnostic image serving as a diagnosis target and a diagnosed image similar to the diagnostic image for comparison , the information processing unit comprising:a diagnostic image input section that inputs the diagnostic image;an operation information obtaining section that obtains display operation history information representing an operation history of a user who controls displaying of the diagnostic image;a query image generation section that extracts a predetermined region of the input diagnostic image to generate a query image;a diagnosed image obtaining section that supplies the generated query image and the display operation history information to a diagnosed image search unit and obtains the diagnosed image obtained as a search result by the diagnosed image search unit; anda display control section that displays the diagnostic image and the obtained diagnosed image for comparison,wherein the diagnosed image search unit includesan image feature amount extraction section that extracts an image feature amount of the query image,a search section that retrieves diagnosed images each of which includes a sub-image with an image feature amount ...

Image processing device, method and program for moving gesture recognition using difference images

An image processing device includes a difference image generation unit which generates a difference image by obtaining a difference between frames of a cutout image which is obtained by cutting out a predetermined region on a photographed image; a feature amount extracting unit which extracts a feature amount from the difference image; and a recognition unit which recognizes a specific movement of an object on the photographed image based on the feature amount which is obtained from the plurality of difference images which are aligned in time sequence.

Robot device, robot device action control method, external force detecting device and external force detecting method

A robot is proposed which has a speech recognition unit to detect information supplied simultaneously with or just before or after detection of a touch by a touch sensor, an associative memory/recall memory to store action made correspondingly to the touch and input information (speech signal) detected by the speech recognition unit in association with each other, and an action generator to control the robot to make action recalled by the associative memory/recall memory based on a newly acquired input information (speech signal). The robot has also a sensor data processor to allow the robot to act correspondingly to the touch detection by the touch sensor. Thus, the robot can learn action in association with an input signal such as speech signal.

Close range natural user interface system and method of operation thereof

Image Processing Apparatus, Image Processing Method, Program, and Recording Medium

An image processing apparatus includes a detector, a setting unit, and an image generator. The detector detects a target object image region from a first image. When one or more predetermined parameters are applicable to a target object within the region detected by the detector, the setting unit sets the relevant target object image region as a first region. The image generator then generates a second image by applying predetermined processing to either the image portion within the first region, or to the image portions in a second region containing image portions within the first image that are not contained in the first region.

Robot device and behavior control method for robot device

A robot apparatus causes the emotion in a feeling part ( 130 ) to be changed based on the information acquired by a perception part ( 120 ) to manifest the behavior of information acquisition as autonomous behavior. The robot apparatus includes a behavior control part for causing the robot apparatus to manifest a language acquisition behavior and a meaning acquisition part. The robot apparatus also includes a control part for performing the behavior control of pointing its object of learning. The robot apparatus causes changes in internal states, which are ascribable to the object, to be stored in a memory part in association with the object.

Data processing apparatus, data processing method, and program

A data processing apparatus includes an obtaining unit configured to obtain time-series data from a wearable sensor, an activity model learning unit configured to learn an activity model representing a user activity state as a stochastic state transition model from the obtained time-series data, a recognition unit configured to recognize a current user activity state by using the activity model of the user obtained by the activity model learning unit, and a prediction unit configured to predict a user activity state after a predetermined time elapses from a current time from the current user activity state recognized by the recognition unit.

Gesture input device, gesture input method, and program

A gesture input device includes an input unit to which image information representing an action is input. The gesture input device also includes a detection unit that detects the action based on a shape of the input image information. The gesture input device further includes a prediction unit that predicts one or more gestures based on a detection result of the action. In addition, the gesture input device includes a notification unit that notifies an action to be performed next to input the predicted one or more gestures.

Robot device and behavior control method for robot device

Information processing apparatus, method and program

An information processing apparatus, which creates a tree structure used by a recognition apparatus which recognizes specific information using the tree structure, including a memory unit which stores data including the information to be recognized and data not including the information so as to correspond to a label showing whether or not the data includes the information, a recognition device which recognizes the information and outputs a high score value when the data including the information is input, and a grouping unit which performs grouping of the recognition devices using a score distribution obtained when the data is input into the recognition devices.

Information processing device, action determination method, and program

More natural communication and interaction are enabled. The autonomous system (100) includes an action decision unit (140) that decides, based on an attention level map (40) in which an attention level indicating the degree of attention for each position in a predetermined space is set, the action which a drive mechanism is caused to perform.

Robot apparatus, face recognition method, and face recognition apparatus

Image processing device for detecting a face or head region, a clothing region and for changing the clothing region

An image processing device includes a clothing extractor extracting a face or head portion from an input image, the face or head portion being a region estimated to be a face or head image, and extracting a clothing region from a region immediately below the face or head portion, the clothing region being a region estimated to be a clothing image, and a clothing converter changing clothing in the input image by performing predetermined image processing on an image in the clothing region in the input image.

Gesture input device, gesture input method, and program

【課題】ジェスチャの種類および／または複雑度が増してもジェスチャを適切に入力可能な、ジェスチャ入力装置、ジェスチャ入力方法およびプログラムを提供する。 【解決手段】ユーザの動作を表す画像情報および音声情報のうち少なくとも一方が入力される入力部１１と、入力された画像情報および音声情報のうち少なくとも一方から、ユーザの動作を検出する検出部１３と、動作の検出結果に基づき、ユーザが入力しようとする１以上のジェスチャを予測する予測部１９と、予測された１以上のジェスチャを入力するために、ユーザが次にとるべき動作をユーザに通知する通知部２１とを備える。 【選択図】図１

Integrated interactive segmentation with spatial constraint for digital image analysis

An integrated interactive segmentation with spatial constraint method utilizes a combination of several of the most popular online learning algorithms into one and implements a spatial constraint which defines a valid mask local to the user's given marks. Additionally, both supervised learning and statistical analysis are integrated, which are able to compensate each other. Once prediction and activation are obtained, pixel-wised multiplication is conducted to fully indicate how likely each pixel belongs to the foreground or background.

Information processing device, action determination method, and program

Device, method, and computer-readable storage medium for compositing images

An image processing apparatus includes a detector, a setting unit, and an image generator. The detector detects a target object image region from a first image. When one or more predetermined parameters are applicable to a target object within the region detected by the detector, the setting unit sets the relevant target object image region as a first region. The image generator then generates a second image by applying predetermined processing to either the image portion within the first region, or to the image portions in a second region containing image portions within the first image that are not contained in the first region.

Information processing device, information processing method, and program

An information processing device includes a feature amount extraction unit configured to extract each feature amount from a connected image generated by connecting images photographed from different viewpoints; and a specific object recognition unit configured to perform a process of determining a position of a specific object based on the feature amount extracted by the feature amount extraction unit. The feature amount extraction unit performs a feature amount extraction process to which a separated filter in which filter-formed regions are set to be separated is applied.

Face recognition with Gabor filters

Close range natural user interface system and method of operation thereof

Integrated interactive segmentation with spatial constraint for digital image analysis

An integrated interactive segmentation with spatial constraint method utilizes a combination of several of the most popular online learning algorithms into one and implements a spatial constraint which defines a valid mask local to the user's given marks. Additionally, both supervised learning and statistical analysis are integrated, which are able to compensate each other. Once prediction and activation are obtained, pixel-wised multiplication is conducted to fully indicate how likely each pixel belongs to the foreground or background.

ROBOT DEVICE, FACE DETECTION METHOD AND FACIAL DETECTION DEVICE

Information processing device and method, and program

An information processing device includes a first calculation unit which calculates a score of each sample image including a positive image in which an object as an identification object is present and a negative image in which the object as the identification object is not present, for each weak identifier of an identifier including a plurality of weak identifiers, a second calculation unit which calculates the number of scores when the negative image is processed, which are scores less than a minimum score among scores when the positive image is processed; and an realignment unit which realigns the weak identifiers in order from a weak identifier in which the number calculated by the second calculation unit is a maximum.

Information processing device, information processing method, and program

An information processing device includes a feature amount extraction unit configured to extract each feature amount from a connected image generated by connecting images photographed from different viewpoints; and a specific object recognition unit configured to perform a process of determining a position of a specific object based on the feature amount extracted by the feature amount extraction unit. The feature amount extraction unit performs a feature amount extraction process to which a separated filter in which filter-formed regions are set to be separated is applied.

Data processing apparatus, data processing method, and program

【課題】未来の所望の時刻におけるユーザの活動状態の複数の可能性を確率的に予測することができるようにする。 【解決手段】センサ入力部１１は、ウェアラブルセンサから時系列データを取得する。ユーザ活動モデル学習部１３は、取得された時系列データから、ユーザの活動状態を表す活動モデルを、確率的状態遷移モデルとして学習し、学習の結果得られたパラメータをユーザモデルパラメータ記憶部１４に供給する。ユーザ活動認識部１５は、学習により得られたユーザの活動モデルを用いて、現在のユーザの活動状態を認識する。ユーザ活動予測部１６は、認識された現在のユーザの活動状態から、現在から所定時間経過後のユーザの活動状態を予測する。本発明は、例えば、ユーザの行動を予測して、制御対象装置に予測した行動に対応する処理を行わせるデータ処理装置に適用できる。 【選択図】図２

Information processing device and method, program and recording medium for identifying a gesture of a person from captured image data

An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points: an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amolmts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation.

Information processing apparatus, information processing method, and program

Provided is an information processing apparatus including: a motion control unit (107) that controls a motion of an autonomous moving body (10), in which, when transmitting/receiving internal data related to the autonomous moving body, the motion control unit causes the autonomous moving body to express execution of the transmission/reception of the internal data by an action.

Information processing apparatus and method for processing information

There is provided an information processing apparatus including a reality determiner that determines whether an object detected on the basis of sensing data is a real object or an unreal object, and a controller that performs predetermined control on the basis of a result of the determination made by the reality determiner.

情報処理装置、情報処理方法およびプログラム

【課題】追跡の安定性を向上可能な、情報処理装置、情報処理方法およびプログラムを提供する。 【解決手段】追跡対象Ｏを相異なる撮影条件で捉えた学習画像Ｉｓを撮影条件とともに入力する学習画像入力部１１と、追跡対象Ｏの形状特徴および色特徴を少なくとも部分的に重ねてなる１以上の統合特徴について、撮影条件に応じて１以上統合特徴の学習画像Ｉｓ上での位置、サイズ・角度の少なくともいずれかを規定するパラメータを変化させながら、学習画像Ｉｓとの応答を算出する特徴応答算出部１２と、応答の算出結果に基づき学習画像Ｉｓ上での１以上の統合特徴の空間分布を把握し、撮影条件とパラメータの関係、および統合特徴同士の空間関係を評価して、追跡対象Ｏの特徴を学習する特徴学習部１３と、特徴の学習結果を格納する特徴格納部１４とを備える。 【選択図】図１

画像処理装置および方法、記録媒体、並びにプログラム

【課題】肌色を正確に抽出できるようにする。 【解決手段】 色空間変換部１１は、教師画像を構成するYUV色空間で表現される画素値を、肌色を定義するモデルを生成しやすいTSL色空間で表現される画素値に変換し、画素値抽出部１２は、TSL色空間で表現される画素値により構成される教師画像より画素値を抽出し、アウトライヤ除去部１４は、抽出された画素値のうち、TSL色空間において、分散計算部１３により計算された分散値に基づいて、ばらつきの大きな画素値を除去し、モデル生成部１５は、ばらつきの大きな画素値が除外されている、抽出された、TSL色空間で所定の色を表現する画素値の分布モデルを生成し、テーブル生成部１６は、分布モデルに基づいて、肌色を定義するTSL色空間の画素値よりテーブルを生成してテーブル記憶部２に記憶させる。本発明は、画像認識装置に適用することができる。 【選択図】図１

Information processing device and method, program and recording medium for identifying a gesture of a person from captured image data

An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points: an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation.

Information processing device, information processing method, and information processing program

An information processing device includes: a joint detection unit that detects a joint of a person striking a pose to imitate a pose of a robot device including a joint; a human body joint angle estimation unit that estimates an angle of the joint of the person; and a mapping learning unit that learns mapping between the angle of the joint of the person and an angle of the joint of the robot device in the pose.

Information processing device, information processing method, and program

Information processing unit, information processing method, and program

An information processing unit includes: a diagnostic image input section that inputs the diagnostic image; an operation information obtaining section that obtains display operation history information representing an operation history of a user who controls displaying of the diagnostic image; a query image generation section that extracts a predetermined region of the input diagnostic image to generate a query image; a diagnosed image obtaining section that supplies the generated query image and the display operation history information to a diagnosed image search unit and obtains the diagnosed image obtained as a search result by the diagnosed image search unit; and a display control section that displays the diagnostic image and the obtained diagnosed image for comparison.

Information processing device and method, program and recording medium for identifying a gesture of a person from captured image data

An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points: an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation.

Information processing device and information processing method

An information processing device includes: a joint detection unit that detects a joint of a person striking a pose to imitate a pose of a robot device including a joint; a human body joint angle estimation unit that estimates an angle of the joint of the person; and a mapping learning unit that learns mapping between the angle of the joint of the person and an angle of the joint of the robot device in the pose.

Information processing device, action decision method and program

More natural communication and interaction are enabled. The autonomous system (100) includes an action decision unit (140) that decides, based on an attention level map (40) in which an attention level indicating the degree of attention for each position in a predetermined space is set, the action which a drive mechanism is caused to perform.

ロボット装置、情報提供方法、プログラム及び記録媒体

(57)【要約】 【課題】 ロボット装置が使用者が望む情報を的確に提 供することができる。 【解決手段】 ロボット装置は、自律的な行動をするた めの駆動部２と、外部情報を検出する自発的情報収集部 １０と、自発的情報収集部１０が検出した外部情報とさ れる知識情報が記憶される知識データベース３と、抽出 用データとされる抽出データベース８に基づいて、知識 データベース３に記憶された知識情報から所定の情報を 検索する情報抽出部５と、情報抽出部５により検索され た所定の情報（認識情報）を外部出力する情報提示部６ とを備える。

Information processing device, information processing method, and information processing program

An information processing device (1) includes a registration information storage unit (112), an acquisition unit (122), a presentation unit (123), and a registration unit (124). The registration information storage unit (112) stores registration information related to an object to be a recognition target. The acquisition unit (122) acquires attribute information indicating a property of a new object to be a recognition target in accordance with a message of advice received from a user. The presentation unit (123) presents the attribute information acquired by the acquisition unit (122) to the user. In accordance with a registration instruction received from the user, the registration unit (124) associates attribute information with name information designated by the user, and registers the associated information in the registration information storage unit (112) as registration information.

画像処理システム、学習装置および方法、画像認識装置および方法、記録媒体、並びにプログラム

【課題】 簡単な学習処理により高い精度で画像中の物体認識を実現できるようにする。 【解決手段】 特徴点Ｐ 1 を基準とするとき、特徴点Ｐ 1 の主方向αに対して、角度（α−θ）から角度（α＋θ）の範囲内で、かつ、最も近い特徴点の特徴量を特徴点Ｐ 1 の特徴量に加えることで、特徴点Ｐ１の特徴量に空間における幾何学的な拘束を含ませる。特徴点Ｐ 2 乃至Ｐ 6 においては、角度（α−θ）から角度（α＋θ）の範囲内で、かつ、特徴点Ｐ 1 に最も近い特徴点は、特徴点Ｐ 2 であるので、特徴点Ｐ 1 の特徴量と特徴点Ｐ 2 の特徴量とを合成させ、合成された特徴量を特徴点Ｐ 1 の特徴量とする。結果として、各特徴点の特徴量は、幾何学的に拘束されることになるので、簡単な学習処理で、認識処理における精度を向上させることが可能となる。本発明は、画像認識装置に適用することができる。 【選択図】 図６

Head-mounted device for user interactions in an amplified reality environment

Information processing device, information processing method, and program

[Object] To provide an information processing apparatus, an information processing method, and a program that are capable of presenting a learning status of object recognition learning to the user in an understandable manner.[Solving Means] An information processing apparatus includes a learning unit, an assessment unit, and a signal generation unit. The learning unit performs recognition learning of an object in an image captured by a camera. The assessment unit assesses a progress status of the recognition learning of a target region of the object. The signal generation unit generates a presentation signal for presenting the target region and the progress status to a user.

Head-mounted device for user interactions in an amplified reality environment

An information processing apparatus includes circuitry that is configured to provide a user interface to control a plurality of controllable objects. The user interface is associated with a gesture recognition area that is defined by a predetermined detection area of a sensor. The gesture recognition area is divided into a plurality of gesture recognition sub-areas based on a number of the controllable objects to be controlled by the user interface. The circuitry is further configured to detect a predetermined gesture within the predetermined detection area, determine the gesture recognition sub-area in which the predetermined gesture is detected, and perform an operation on one of the controllable objects based on the detected predetermined gesture and the determined gesture recognition sub-area in which the predetermined gesture is detected.

物体認識装置及び方法並びにロボット装置

(57)【要約】 【課題】一般家庭等の実環境において３次元物体の認識 を精度良く行い難い問題があった。 【解決手段】物体認識装置及び方法において、認識対象 の物体を、所定の撮像手段に対して予め定められた所定 の空間位置に移動させて、当該空間位置において所定状 態に保持し、撮像手段の出力に基づいて物体を認識し、 認識できなかったときには当該物体を学習するようにし た。またロボット装置において、周囲を撮像する撮像手 段と、撮像手段の出力に基づいて認識すべき物体を選択 し、当該選択した物体を撮像手段に対して予め定められ た所定の空間位置に移動させて所定状態に保持するよう に、腕部の動きを制御する制御手段と、撮像手段の出力 に基づいて物体を認識し、認識できなかったときには当 該物体を学習する認識学習手段とを設けるようにした。

Information processing device and method, program and recording medium for identifying a gesture of a person from captured image data

An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points: an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation.

Information processing device and method, program and recording medium for identifying a gesture of a person from captured image data

An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points; an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation.

Image processing device and method for moving gesture recognition using difference images

An image processing device includes a difference image generation unit which generates a difference image by obtaining a difference between frames of a cutout image which is obtained by cutting out a predetermined region on a photographed image; a feature amount extracting unit which extracts a feature amount from the difference image; and a recognition unit which recognizes a specific movement of an object on the photographed image based on the feature amount which is obtained from the plurality of difference images which are aligned in time sequence.

Image processing system, image processing apparatus, image processing method, and program

An image processing system includes a storing section that stores a database in which specific pose data representing each of specific poses of a human, and effect manipulation data specifying each of manipulations applied to an image are registered in association with each other, a human region detecting section that detects a human region that is a region where a human appears in an image on which to perform image processing, a human pose recognizing section that recognizes a pose of the human in the human region detected by the human region detecting section, a matching section that finds the specific pose data matching the pose recognized by the human pose recognizing section, by referencing the database, and a manipulating section that applies a manipulation to the image on the basis of the effect manipulation data associated with the specific pose data found by the matching section.