H04N1/6086

ADJUSTING AN IMAGE ACCORDING TO AMBIENT LIGHT CONDITIONS
20170324940 · 2017-11-09 ·

An image of an object under a first illuminant is captured. The color of the ambient light at a device on which the image is to be displayed is identified. The image data is adjusted to compensate for the color of the ambient light as well as for the color of the first illuminant. An image based on the adjusted image data can then be displayed on the device. As such, the desired perception of the colors in the displayed image can be managed so that image quality is maintained even if the image is displayed under different ambient lighting conditions.

Color matching with shade detection
09769393 · 2017-09-19 · ·

This disclosure is directed to color matching with shade detection. A method of color matching can include: receiving a camera image of a target, the camera image being collected in the presence of flash illumination; receiving a color sensor spectral measurement of the target, the color sensor spectral measurement being collected in the presence of flash illumination; determining specular and diffuse fractions of a flash intensity profile of the camera image of the target; determining parallax based upon a detected location of a flash centroid within the camera image of the target; converting the parallax to a range measurement for the target; calculating an expected white level for the target based upon the specular and diffuse fractions and the range measurement for the target; and calculating a shade of a detected color based upon the color sensor spectral measurement and the expected white level for the target.

WHITE BALANCE WITH REFERENCE ILLUMINANTS
20210409667 · 2021-12-30 ·

Introduced here are computer programs and associated computer-implemented techniques for achieving high-fidelity color reproduction in the absence of any known reflectance spectrums. That is, high-fidelity color reproduction can be achieved without portable references, such as gray cards and color checkers. To accomplish this, a new reference spectrum—the “reference illuminant spectrum”—is introduced into scenes to be imaged by image sensors. The reference illuminant spectrum is created by a multi-channel light source whose spectral properties are known.

Image processing apparatus, image processing method, storage medium, and image forming apparatus

Disclosed is an image processing apparatus including: a derivation unit configured to derive a target luminance characteristic based on a viewing condition of an image and a print luminance characteristic predicted based a reflection characteristic corresponding to data thereon; a unit configured to generate print image data on an image by converting input image data by using a tone conversion characteristic that is set based on these characteristics, in which the derivation unit derives, in a case where a reproduction range of an illumination intensity in the print luminance characteristic is different, the target luminance characteristic so that a liner area of an output luminance in a case where the reproduction range is relatively large becomes large.

COLOR PARAMETER GENERATION APPARATUS, EXECUTION APPARATUS AND NON-TRANSITORY COMPUTER-READABLE RECORDING MEDIUM
20210377413 · 2021-12-02 · ·

A color parameter generation apparatus includes a hardware processor that generates color parameters to be used for printing a sample image based on a read image, in which the hardware processor determines a flare degree at a predetermined position of the read image, and executes predetermined processing for correcting the color parameters in the predetermined position based on the determined flare degree.

Color correction device

A linear matrix circuit generates a second R signal, a second G signal, and a second B signal by performing a matrix operation of a correction coefficient of 3 rows×3 columns including first to third correction coefficients, fourth to sixth correction coefficients, and seventh to ninth correction coefficients on a first R signal, a first G signal, and a first B signal. An R coefficient corrector performs correction so that the first correction coefficient to be multiplied by the first R signal is caused to be close to 1 and the second and third correction coefficients to be respectively multiplied by the first G signal and the first B signal are caused to be close to 0, as a first difference value obtained by subtracting the first G signal from the first B signal increases when the first difference value exceeds a first threshold.

Method for building a security image by multiplexing color images

A method for building a security image for a security structure of a security document from multiplexing color images, including selecting a marking method capable of producing sets of colors on the security document comprising different colors that can be displayed according to illumination/observation modes of the security structure, establishing a plurality of color sets that can be displayed by the security structure in a plurality of the different illumination/observation modes, distributing the color sets in a plurality of groups of color sets, establishing combinations of groups of color sets having at least one color set in common across the number of different illumination/observation modes, selecting a combination of a group of color sets based on the number of desired illumination/observation modes and the number of colors per color image, and determining the color images to multiplex by means of the combination of the group of color sets selected.

Methods and Apparatuses of Contrastive Learning for Color Constancy
20220164601 · 2022-05-26 ·

A contrastive learning method for color constancy employs a fully-supervised construction of contrastive pairs, driven by a novel data augmentation. The contrastive learning method includes receiving two training images, constructing positive and negative contrastive pairs by the novel data augmentation, extracting representations by a feature extraction function, and training a color constancy model by contrastive learning representations in the positive contrastive pair are closer than representations in the negative contrastive pair. The positive contrastive pair contains images having an identical illuminant while negative contrastive pair contains images having different illuminants. The contrastive learning method improves the performance without additional computational costs. The desired contrastive pairs allow the color constancy model to learn better illuminant feature that are particular robust to worse-cases in data sparse regions.

Method for Providing a Decor Combination and System
20220134798 · 2022-05-05 ·

The invention relates to a method for providing a decorative combination for furniture items and/or interior fixtures. The problem addressed of providing a method for producing a decorative combination, for which the matching of said combination with respect to a change of illuminant is further simplified, is solved by a method including the steps: carrying out colorimetric measurements, under at least two different illuminants, on a first decorative element of a first fixture; determining a reference colour change of the first decorative element when the change between the at least two different illuminants is made; printing a second decorative element onto a second fixture, a selection and/or combination of inks for the printing process being carried out on the basis of a colour change of the inks under a change of illuminant, such that a colour change of the second decorative element under the change of the at least two different illuminants is compared to the reference colour change. The invention also relates to a system, in particular for carrying out a method according to the invention, the system including a colorimeter, a printer and a control device.

Color correspondence information generating system, program, and method of generating color correspondence information

A color correspondence information generating system includes an object database that stores correspondences between recognition information and color characteristic information about first objects recognized by the recognition information; an object recognition section that recognizes the first objects in the first image from the first image and the recognition information, and outputs image regions of the first objects in the first image and first color characteristic information; and a color correspondence information generation section that generates the color correspondence information using the color information and the first color characteristic information of pixels in the image regions. The color characteristic information and the recognition information have a one-to-one correspondence relation with each other, or the color characteristic information is the recognition information itself.