This disclosure involves training generative adversarial networks to shot-match two unmatched images in a context-sensitive manner. For example, aspects of the present disclosure include accessing a trained generative adversarial network including a trained generator model and a trained discriminator model. A source image and a reference image may be inputted into the generator model to generate a modified source image. The modified source image and the reference image may be inputted into the discriminator model to determine a likelihood that the modified source image is color-matched with the reference image. The modified source image may be outputted as a shot-match with the reference image in response to determining, using the discriminator model, that the modified source image and the reference image are color-matched.

An electronic device is disclosed. The electronic device includes at least one processor electrically connected with an image sensor and a memory. The memory stores instructions, when executed, causing the processor to obtain an image through the image sensor, segment the obtained image into the plurality of regions, calculate values of a first parameter for each of the plurality of regions based on the reference color components indicating a representative color of each of the plurality of regions, calculate values of a second parameter for each of the plurality of regions based on first pixel values output from the plurality of first light receiving elements included in each of the plurality of regions and second pixel values output from the plurality of second light receiving elements, determine a type of a light source corresponding to each of the plurality of regions, based on a value of the second reference parameter included in data about the correlationship corresponding to the calculated values of the first parameter and values of the second parameter calculated for each of the plurality of regions, and determine a type of a light source of the image based on the determined types of the light source. In addition, various other embodiments recognized from the specification are also possible.

Methods and systems are described for processing an image captured with an image sensor, such as a camera. In one embodiment, an estimated ambient light level of the captured image is determined and used to compute an optical-optical transfer function (OOTF) that is used to correct the image to preserve an apparent contrast of the image under the estimated ambient light level in a viewing environment. The estimated ambient light level is determined by scaling pixel values from the image sensor using a function that includes exposure parameters and a camera specific parameter derived from a camera calibration.

A system for the high-fidelity display of artwork images simulates lighting conditions (such as by, for example, varying the colour temperature, intensity, and/or lighting direction) and, for each lighting condition, compares an image of an artwork against an image of a digital display thereof. The system calculates an image adjustment (such as, for example, brightness/contrast, levels, tonal curves, exposure, vibrance, hue/saturation and/or colour balance) to minimise perceived visual differences between the original artwork and the image of a digital display thereof under the same environmental lighting conditions. As such, when displayed at a display location, the artwork image may be adjusted using the calculated image adjustment according to the actual lighting conditions at the display location.

An image processing apparatus includes: an input device to which a pre-color conversion image and a post-color conversion image are input; and a processor. The processor is configured to execute a program to extract color data in a certain region of at least one of the pre-color conversion image and the post-color conversion image, change at least one of a position and a range of the certain region in a case where the extracted color data meet a certain condition, and prepare a color conversion model using color data in the certain region after being changed.

The present invention relates to an electronic device, and a method for processing an image according to a camera photographing environment and scene by using the same, and the electronic device according to various embodiments of the present invention comprises a camera module, a memory, and a processor electrically connected to the camera module and the memory, wherein the processor can be configured to: extract a first parameter for first image data obtained using the camera module; detect situation information on the electronic device by using a sensor or a microphone functionally connected to the electronic device; detect a scene, corresponding to the first image data, among a plurality of predefined scenes; obtain a second parameter on the basis of the first parameter, the situation information, and the scene; generate, on the basis of the second parameter, second image data obtained using the camera module; and display the second image data by using a display functionally connected to the electronic device. Other various embodiments, in addition to the various embodiments of the present invention, are possible.

Chromatic calibration of a device having an embedded camera proceeds by illuminating a plurality of color references with at least one light source. Images of the respective illuminated color references are captured with the embedded camera. Color calibration data from are determined from the captured images and the color calibration data are stored in association with an identifier of the device.

An article having a retroreflective marking and non-retroreflective, traditional marking is provided. The article presents as having a first design when under common overhead or environmental lighting, and having a second different design when the retroreflective marking is illuminated with a direct light, reflecting the light back to its source to cause an illuminated appearance.

This disclosure involves training generative adversarial networks to shot-match two unmatched images in a context-sensitive manner. For example, aspects of the present disclosure include accessing a trained generative adversarial network including a trained generator model and a trained discriminator model. A source image and a reference image may be inputted into the generator model to generate a modified source image. The modified source image and the reference image may be inputted into the discriminator model to determine a likelihood that the modified source image is color-matched with the reference image. The modified source image may be outputted as a shot-match with the reference image in response to determining, using the discriminator model, that the modified source image and the reference image are color-matched.

An ambient light color sensing device adapted to determine color of ambient light and method for calibrating thereof. The ambient light color sensing device comprises a memory, a processor, and a light color sensor having a plurality of channels that detect light at different wavelengths to produce sensor readings. Wherein the processor receives sensor readings from the light color sensor, determines an interpolated spectral power distribution from the received sensor readings, converts the interpolated spectral power distribution to at least one measured light color value that quantifies color of light, and determines at least one calibrated light color value by correlating the at least one measured light color value through a calibration matrix.