An electronic device includes at least one memory storing instructions; and at least one processor which, upon execution of the instructions, configures the at least one processor to function as: an estimation unit configured to estimate a gaze area of a user; and a selection unit configured to select a selection area from one or more candidate areas based on the gaze area.

Learning-based color correction (e.g., auto while balance (AWB)) procedures may be trained based on datasets from different sensors using a pre-processing procedure. Each input pixel may be converted into a sensor-independent representation through multiplication by a sensor-specific color conversion function (e.g., a 3×3 matrix). The sensor-specific color conversion function may be obtained based on a sensor type. For example, the sensor-specific color conversion function, such as a 3×3 matrix, may be obtained by a corresponding sensor calibration procedure performed using laboratory images of a color checker chart subject to standard illuminants. Parameters of the sensor-specific color conversion function may be optimized in a chromaticity space. For instance, a sensor-specific 3×3 matrix for color conversion may be optimized using a distance in the chromaticity space between calibration data (e.g., calibration configurations) and sensor-independent targets (e.g., a target sensor-independent representation for each calibration configuration).

Dual cameras that simultaneously capture RGB and IR images of a scene can be used to remove glare from the RGB image, transformed to a YUV image, by substituting a glare region in the luminance component of the YUV image with the pixel values in a corresponding region of the IR image. Further, color information in the glare region may be adjusted by averaging over or extrapolating from the color information in the surrounding region.

In a vehicle-mounted camera system, an appropriate white balance correction processing according to a situation is executed to a long exposure time image and a short exposure time image shot in variously changing illumination environments. A vehicle-mounted camera system includes a vehicle-mounted camera that performs relatively long exposure time shooting and short exposure time shooting, a signal processing device (signal processing device) that executes a white balance correction processing for each of a long exposure time image and a short exposure time image, composes these images after the white balance correction processing, and generates a high dynamic range image, and a system control part (processing switch device) that obtains an illumination environment in which the vehicle is placed, and switches the white balance correction processing for the long exposure time image and the white balance correction processing for the short exposure time image according to the illumination environment.

An optical system includes a multispectral sensor; an optical filter including a plurality of optical channels that is disposed over the multispectral sensor; and a lens that is disposed over the optical filter. The lens is configured to direct first light that originates from a scene to the optical filter. The optical filter is configured to pass one or more portions of the first light to the multispectral sensor. The multispectral sensor is configured to generate, based on the one or more portions of the first light, spectral data associated with the scene.

An image acquisition apparatus including: a stage on which a specimen is mounted; an objective lens that collects light from the specimen; a stage driving part that drives the stage; an image capturing unit that acquires an image by photographing the light collected by the objective lens; an image-generating unit that generates a pasted image by pasting the captured image acquired by the image capturing unit; a storage unit that stores the pasted image; a color-difference calculating unit that calculates a degree of dissimilarity between a color of the pasted image and a color of the captured image prior to pasting; and a color-difference correcting unit that corrects the color of the captured image so as to match the color of the pasted image, on the basis of the calculated degree of dissimilarity.

Disclosed examples include integrated circuits, merge circuits and methods of processing multiple-exposure image data, in which a single pre-processing circuit is used for pre-processing first input exposure data associated with a first exposure of the image, and then for pre-processing second input exposure data associated with a second exposure of the image, and the first and second pre-processed exposure data are merged to generate merged image data for tone mapping and other post-processing. An example merge circuit includes a configurable gain circuit to apply a gain to the first and/or second exposure data, as well as a configurable weighting circuit with a weight calculation circuit and a motion adaptive filter circuit to compute a first and second weight values for merging the pre-processed first and second exposure data.

A color correction data generating apparatus capable of performing color matching not depending on changes in the photographing position of the camera and the color tone of the light source is provided. The color correction data generating apparatus, which obtains a plurality of images obtained by photographing a predetermined subject with a plurality of image pickup apparatuses, includes at least one processor and/or circuit configured to function as following units, an output unit inputting an image of a predetermined subject region included in the obtained image into a learned model that machine learning has been already performed, and outputting an inferred image obtained by inferring the image of the predetermined subject region included in an image obtained when photographing the predetermined subject under a prescribed photographing condition, and a generating unit generating color correction data that matches color characteristics of a plurality of inferred images outputted by the output unit.

An image processing apparatus comprises an input unit configured to input an image; an acquisition unit configured to acquire a parameter for adjusting an image quality, reference environment information serving as a reference when adjusting the image quality by applying the parameter, and shooting environment information representing an environment upon shooting the image; an adjustment unit configured to adjust the image by using the parameter; and a determination unit configured to determine, based on a difference between the reference environment information and the shooting environment information, whether adjustment by the parameter is necessary.

Disclosed is a method and apparatus of illuminant estimation referencing characterized facial color features in a digital image. Example embodiments of automatic white balance of the digital image leveraging the illuminant estimation are illustrated.