IMAGE DATA PRE-PROCESSING FOR NEURAL NETWORKS

An image processor comprising an input module for receiving image data from an image sensor; an image processing module arranged to perform one or more operations on at least a portion of the image data to generate processed image data; and a characteristic processing module arranged to perform one or more characteristic processing operations on at least a portion of the characteristic data to generate processed characteristic data. The portion of the characteristic data is associated with the portion of the image data; the one or more characteristic processing operations are associated with the one or more image processing operations. The image processor further comprises an output module for outputting the processed image data and processed characteristic data. 1. An image processor comprising:an input module for receiving image data from an image sensor;an image processing module arranged to perform at least one image processing operation on at least a portion of the image data to generate processed image data;a characteristic processing module arranged to perform at least one characteristic processing operation on at least a portion of characteristic data to generate processed characteristic data, the portion of characteristic data being associated with at least a corresponding portion of the image data captured by the image sensor; andan output module for outputting processed image data and processed characteristic data to a neural processing unit arranged to generate an output using at least one neural network; the at least one characteristic processing operation is associated with the at least one image processing operation; and', 'the processed image data and processed characteristic data being configured for use by the at least one neural network., 'wherein2. The image processor of claim 1 , wherein the characteristic processing module and the image processing module perform the at least one characteristic processing operation and the at least one image ...

CONTRAST-BASED AUTOFOCUS

A method for contrast-based autofocus of an image capture device. The method includes obtaining sensor data representative of an image captured by the image capture device, wherein the sensor data comprises pixel values from respective sensor pixels of an image sensor of the image capture device. A subset of the pixel values is dynamically selected to generate selected sensor data representative of the subset of the pixel values. The selected sensor data is processed to generate contrast data representative of a contrast-based characteristic of at least a portion of the image. The contrast data is processed to determine a focus setting for the image capture device. 1. A method for contrast-based autofocus of an image capture device , the method comprising:obtaining sensor data representative of an image captured by the image capture device, wherein the sensor data comprises pixel values from respective sensor pixels of an image sensor of the image capture device;dynamically selecting a subset of the pixel values to generate selected sensor data representative of the subset of the pixel values;processing the selected sensor data to generate contrast data representative of a contrast-based characteristic of at least a portion of the image; andprocessing the contrast data to determine a focus setting for the image capture device.2. The method according to claim 1 , wherein dynamically selecting the subset of the pixel values comprises setting a further subset of the pixel values to a predetermined value claim 1 , wherein optionally the predetermined value is zero.3. The method according to claim 1 , comprising dynamically selecting the subset of the pixel values based on intensity data representative of an intensity of light received by at least one of the sensor pixels.4. The method according to claim 1 , wherein the image capture device comprises a colour filter array comprising a pattern of colour filter elements corresponding to respective sensor pixels of the ...

PIXEL CORRECTION

A method and apparatus for image processing, the method comprising obtaining input image data comprising a plurality of pixel intensity values representing a respective plurality of pixel locations, obtaining pixel location data identifying one or more pixel locations represented by compromised pixel intensity values, generating interpolated image data comprising improved pixel intensity values, storing improved image data comprising at least the interpolated image data, and detecting one or more further compromised pixel intensity values based on the improved image data. 1. A method comprising:obtaining input image data representative of at least a portion of an image, the input image data comprising a plurality of pixel intensity values representing a respective plurality of pixel locations;obtaining pixel location data identifying one or more pixel locations represented by one or more respective compromised pixel intensity values;generating interpolated image data comprising one or more improved pixel intensity values representing the one or more identified pixel locations based on the input image data and the pixel location data;storing improved image data comprising at least the interpolated image data; anddetecting one or more further compromised pixel intensity values based on the improved image data.2. The method of claim 1 , wherein the pixel location data identifies one or more static defect pixel locations.3. The method of claim 1 , wherein the pixel location data identifies one or more phase detection autofocus pixel locations.4. The method of claim 1 , wherein the pixel location data identifies one or more static defect pixel locations and one or more phase detection autofocus pixel locations.5. The method of claim 4 , wherein obtaining the pixel location data comprises generating the pixel location data based on predetermined phase detection autofocus pixel locations and predetermined static defect pixel locations.6. The method of claim 1 , wherein ...

Contrast-based autofocus

Focus setting determination

Image data pre-processing for neural networks

An image processor comprising an input module for receiving image data from an image sensor; an image processing module arranged to perform one or more operations on at least a portion of the image data to generate processed image data; and a characteristic processing module arranged to perform one or more characteristic processing operations on at least a portion of the characteristic data to generate processed characteristic data. The portion of the characteristic data is associated with the portion of the image data; the one or more characteristic processing operations are associated with the one or more image processing operations. The image processor further comprises an output module for outputting the processed image data and processed characteristic data.

Akilli i̇laç kutusu

Bu buluş, ilaç kullanım bilgilerini internet aracılığıyla güvenli bir şekilde doktora, hasta yakınına, hastaya ve sosyal güvenlik kurumuna iletebilen, doktorun gelen bilgiler ile muayene tarihleri arasında hastanın ilaç alımını değiştirebilmeye olanak sağlayan, ilaç alımlarının sosyal güvenlik kurumu ölçütlerine uygunluğu, tansiyon, şeker, solunum fonksiyon testi gibi evde yapılan ölçümlerin akıllı ilaç kutusu (1) tarafından aynı ilaç alım bilgileri gibi iletebilen, piyasada bulunan bu ölçüm cihazların kablosuz veri aktarımı olan modelleriyle birlikte çalışabilen, hastaya takılacak bir akıllı bileklik (2) ile hastanın günlük aktivitesinin izlenmesini sağlayan, gerekli olduğu zaman birbirleriyle haberleşerek genişleyebilen akıllı ilaç kutusu (1) ile koordine çalışan, algılayıcı ağ modülü (2.1), atalet ölçüm birimi (2.2), ekran (2.3), nabız ölçer (2.4), pil (2.5), haptik geri bildirim (2.6), SpO2 ölçer (2.7), buton (2.8), acil durum butonu (2.9), bileklik hoparlörü (2.10) ve bileklik mikrofonu (2.11) kısımlarından oluşan akıllı bileklik (2), kablosuz biyolojik veri ölçü cihazları (3), kablolu biyolojik veri ölçü cihazları (4), kablosuz ilaç kutusu genişleme birimi (5) ve kablolu ilaç kutusu genişleme birimi (6) yerel öğelerinden meydana gelen sisteme sahip olup mekanik ilaç haznesi (1.1), ağ geçidi (1.2), algılayıcılar (1.3), güç devresi (1.4), algılayıcı ağ unsuru (1.5), yerel ağ (1.6), Wi-Fi (1.7), GSM (1.8), ekran (1.9), tuş takımı (1.10), ilaç verme bölmesi (1.11), GSM anteni (1.12), algılayıcı ağı anteni (1.13), hoparlör (1.14), mikrofon (1.15), açma kapama butonu (1.16), acil butonu (1.17), LED (1.18), güç soketi (1.19), adaptör (1.20), Wi-Fi anteni (1.21), USB modülü (1.22) kısımlarından oluşan uzaktan kontrol edilebilen ve rapor verebilen akıllı bir ilaç kutusudur.

Focus setting determination

Applying a hill-climbing automatic focus estimation of each of a plurality of image zones by obtaining a first value of a focus metric for each respective image zone using a first image captured with a first focus setting for the camera, and obtaining a second value of a focus metric for the respective image zone using a second image captured with a second focus setting for the camera. The first and second values are processed to obtain an estimated focus setting for the image zone. Further, intensity data representative of a difference in an intensity of light or brightness captured by the camera using the first focus setting and the second focus 210 are used to derive a compensation measure 212, and the second value of the focus metric for the respective image zone is obtained by applying the compensation measure 216 to uncorrected focus data 214 for the image zone. The focus setting is then determined as a weighted sum of different estimated focus settings for the respective image zones.

Focus setting determination

Determining a focus setting for an image capture device by determining a first average estimated lens position for a first image subregion using estimated focus settings for a first set of a plurality of image zones 202; determining a second average estimated lens position for a second image subregion using estimated focus settings for a second set of the plurality of image zones 204. Determining that the first average estimated lens position is larger than the second average estimated lens position (first average estimated focus plane is closer to the camera, indicating foreground focus) 206. The focus setting is determined by performing a weighted sum of the estimated focus setting for the first set of the plurality of image zones 208. The estimated focus settings for an image zone or sub-area of the image are determined by hill climbing by estimating a focus metric in each zone for multiple focus settings and processing these to determine an optimal focus setting in each zone.

Focus setting determination

Determining a focus setting for an image capture device, by, for each of a plurality of image zones: obtaining a first value of a focus metric for the respective image zone using a first image captured with a first focus setting 168; obtaining a second value of the focus metric for the respective image zone using a second image captured with a second focus setting174; and processing the first and second values to obtain an estimated focus setting for each image zone 176. The focus setting is a weighted sum of the estimated focus setting for a plurality of image zones 178. In embodiments the focus metrics are derived from contrast-based data obtained from the captured images. Preferably the weighted sums are based on a dispersion metric for each image zone/region representing the dispersion of the estimated focus setting (e.g. a measure, like standard deviation or variance, of the spread of the distribution of the estimated focus settings). The weighted sum may also depend on the difference between each respective estimated focus setting and an average of the estimated focus settings. Certain zones (such as those with an outlying or unreliable estimate) can be excluded from the weighted sum.

Focus setting determination

A method of determining a focus setting for an image capture device. The method comprises, for each of a plurality of image zones: obtaining a first value of a focus metric for the respective image zone using a first image captured with a first focus setting for the image capture device; obtaining a second value of the focus metric for the respective image zone using a second image captured with a second focus setting for the image capture device; and processing the first value and the second value to obtain an estimated focus setting for the respective image zone. The focus setting is determined by performing a weighted sum of the estimated focus setting for at least two of the plurality of image zones.

Image data pre-processing for neural networks

Image data 310 (e.g. pixel data) obtained from an image sensor undergoes an image processing operation 330i (e.g. white balance, shading correction, tone mapping). Characteristic data (e.g. shot noise, dark current noise, read noise) of the image data is separately processed by applying an operation 330n associated with the image processing operation 330i (so that the result is representative of the characteristic data as it is processed with the image data). The output processed image data and characteristic data 340 is suitable for use by a neural network 350, so that there is no need for the neural network to perform de-noising to distinguish characteristic data from data to be used in training or classification tasks. Image and characteristic data processing may be performed in parallel and, for high dynamic range image data, an exposure mask based on a boundary associated with the HDR data may be generated at the same time.

Focus setting determination

Focus setting determination

Pixel correction