Abstract: A method performed with an image sensor having a pixel array. At least one frame of a scene may be obtained using the pixel array. At least one region of interest (ROI) is identified within the frame. Subsequent frames of the scene are obtained, which involves controlling the pixel array to perform high resolution imaging with respect to the at least one ROI and low resolution imaging using analog binning with respect to remaining regions of the frames.

Abstract: A method performed with an image sensor having a pixel array. At least one frame of a scene may be obtained using the pixel array. At least one region of interest (ROI) is identified within the frame. Subsequent frames of the scene are obtained, which involves controlling the pixel array to perform high resolution imaging with respect to the at least one ROI and low resolution imaging using analog binning with respect to remaining regions of the frames.

Abstract: A camera may include an image sensor configured to capture and measure light of a scene to be imaged. Control circuitry may be configured to control the image sensor to measure instances of the light captured in main exposure windows interspersed with test exposure windows. Timing of the main exposure windows may be adjusted based on luminance levels captured during the test exposure windows, for synchronization with a flickering waveform of the light.

Abstract: A camera may include an image sensor configured to capture and measure light of a scene to be imaged. Control circuitry may be configured to control the image sensor to measure instances of the light captured in main exposure windows interspersed with test exposure windows. Timing of the main exposure windows may be adjusted based on luminance levels captured during the test exposure windows, for synchronization with a flickering waveform of the light.

Abstract: An image processing method includes the operations of receiving N×N raw data from an N×N sub pixel array including a plurality of first exposure pixels and second exposure pixels having different exposure times, respectively; obtaining a difference value between a value obtained by normalizing an interpolated value of the first exposure pixels and an interpolated value of the second exposure pixels for each channel in the N×N sub pixel array based on the N×N raw data; setting a mismatching value to a maximum value among difference values obtained for the respective channels; and setting a corrected value of a central pixel in the N×N sub pixel array based on the N×N raw data and based on the mismatching value and a threshold value.

Abstract: An image processing method includes the operations of receiving N×N raw data from an N×N sub pixel array including a plurality of first exposure pixels and second exposure pixels having different exposure times, respectively; obtaining a difference value between a value obtained by normalizing an interpolated value of the first exposure pixels and an interpolated value of the second exposure pixels for each channel in the N×N sub pixel array based on the N×N raw data; setting a mismatching value to a maximum value among difference values obtained for the respective channels; and setting a corrected value of a central pixel in the N×N sub pixel array based on the N×N raw data and based on the mismatching value and a threshold value.

Abstract: Adjusting confidence score thresholds is described for a speech recognition engine. The speech recognition engine is implemented in multiple computer processes functioning in a computer processor, and is characterized by an associated receiver operating characteristic (ROC) curve. A results confirmation process interprets user confirmation of speech recognition results within a given confidence score threshold to create a confirmed portion of the ROC curve for the speech recognition engine. A curve extension process extends the confirmed portion of the ROC curve by extrapolation of unconfirmed speech recognition results beyond the confidence score threshold to generate an extended ROC curve. A threshold adjustment process adjusts the confidence score threshold based on the extended ROC curve to meet target operating constraints for operating the speech recognition engine to perform automatic speech recognition of user speech inputs.

Abstract: Adjusting confidence score thresholds is described for a speech recognition engine. The speech recognition engine is implemented in multiple computer processes functioning in a computer processor, and is characterized by an associated receiver operating characteristic (ROC) curve. A results confirmation process interprets user confirmation of speech recognition results within a given confidence score threshold to create a confirmed portion of the ROC curve for the speech recognition engine. A curve extension process extends the confirmed portion of the ROC curve by extrapolation of unconfirmed speech recognition results beyond the confidence score threshold to generate an extended ROC curve. A threshold adjustment process adjusts the confidence score threshold based on the extended ROC curve to meet target operating constraints for operating the speech recognition engine to perform automatic speech recognition of user speech inputs.