A system, article, and method to perform light source estimation for image processing includes measuring a compactness of the distribution of the image data to select a light source.

An image sensor is disclosed. The image sensor includes a plurality of pixels, a switch circuit coupled to the pixels and configured to substantially simultaneously output signals output only from pixels having similar characteristics among the pixels in response to a control signal; and a comparison circuit configured to convert the signals output from the switch circuit into digital signals. The pixels having similar characteristics are located across among the plurality of pixels.

A data conversion unit is disclosed which includes: a transformation portion configured to transform R (red), G (green) and B (blue) sub-pixel data signals of input image data into R, G, B and W (white) sub-pixel data signals; and a brightness reinforcement portion configured to adjust brightness of a transformed W sub-pixel data signal included in the transformed R, G, B, and W sub-pixel data signals based on brightness distribution of the input image data.

An image processing apparatus includes a separation unit that separates a high-frequency component and a low-frequency component, a first generation unit that generates a color signal component from the low-frequency component, a second generation unit that generates a color signal component from the low-frequency component, a third generation unit that generates a color signal component used in common for a luminance signal and a chrominance signal, a first tone conversion unit that performs first tone conversion processing on an output of the third generation unit, a color-and-luminance separation unit that generates a luminance signal and a chrominance signal, a second tone conversion unit that performs a second tone conversion on the high-frequency component, and a combining unit that combines outputs of the color-and-luminance separation unit and the second tone conversion unit.

The image processing apparatus includes a first generation unit that generates a color signal component for a luminance signal, a second generation unit that generates a color signal component for a chrominance signal, a first tone conversion unit that performs a first tone conversion, a second tone conversion unit that performs a second tone conversion, a third generation unit that generates a color signal component used in common, and a third tone conversion unit that performs a third tone conversion on a signal after being processed by the third generation unit. The first and second tone conversion units perform tone conversion using a conversion amount smaller than a conversion amount that matches the target curve, and the third tone conversion unit performs tone conversion using a conversion amount corresponding to a difference from the target curve.

To obtain a color signal having a wide dynamic range (i.e., high sensitivity) and color reproducibility similar to human vision characteristics regardless of the amount of the near infrared components contained in light captured by an imaging device. The imaging device is configured to receive light which has transmitted through the filters selectively transmit light having different wavelengths from each other, to generate an output signal RAW0 by converting the received light using the image pickup element 102 having the plurality of pixels, and to remove, by a removal rate E (Rr) determined in accordance with the ratio Rr of near infrared light component calculated for each pixel, the near infrared light component for each pixel from the generated output signal RAW0, to thereby generate an infrared-separated signal (Ra, Ga, Ba).

An image capturing apparatus includes: an image capturing section that outputs first captured-image data obtained by capturing an image at a relatively low ISO speed, and second captured-image data obtained by capturing an image at an ISO speed higher than the ISO speed for the first captured-image data; a color analysis circuit that analyzes a display color included in a display image of the first captured-image data; a color correction instructing circuit that gives an instruction to correct a display color of the second captured-image data according to a result of the analysis; and an image generation circuit that corrects the display color of the second captured-image data so as to generate an image to be displayed.

An image processing circuit for multi-illumination white balance with thumbnail processing. The image processing circuit determines a set of initial weights for a source pixel in a thumbnail image by determining component values for multiple color channels of the source pixel. The image processing circuit determines a set of weights for the source pixel in a weight map for the thumbnail image. Each weight in the set of weights is determined based on corresponding initial weights from the set of initial weights. Each weight in the set of weights represents an intensity level of a respective chrominance class of multiple chrominance classes for the source pixel. The image processing circuit applies the set of weights to values of the color channels of the source pixel to generate color component values of the color channels of a target pixel in a target thumbnail image.

An image processing circuit for multi-illumination white balance with thumbnail processing. The image processing circuit determines a set of initial weights for a source pixel in a thumbnail image by determining component values for multiple color channels of the source pixel. The image processing circuit determines a set of weights for the source pixel in a weight map for the thumbnail image. Each weight in the set of weights is determined based on corresponding initial weights from the set of initial weights. Each weight in the set of weights represents an intensity level of a respective chrominance class of multiple chrominance classes for the source pixel. The image processing circuit applies the set of weights to values of the color channels of the source pixel to generate color component values of the color channels of a target pixel in a target thumbnail image.

Sensor data processing systems and techniques are described. In some examples, a sensor data processing system receives sensor data (e.g., image data). The system receives a sensor data processing parameter that is associated with a sensor data processing function, such as denoising, and that is consistent across the sensor data. The system adjusts a trained machine learning model based on the sensor data processing parameter to generate an adjusted machine learning model. The system processes the sensor data using the adjusted machine learning model to apply the sensor data processing function to the sensor data according to the sensor data processing parameter and to generate processed sensor data (e.g., denoised image data).