Patent classifications
H04N1/6063
DOCUMENT READING DEVICE AND IMAGE FORMING APPARATUS INCLUDING SAME
A document reading device includes red, green, and blue photoelectric transducers; a reader that reads a color image of a document with the photoelectric transducers; and a converter that converts the read color image into a grayscale image. The converter determines the maximum tone value MAX(RGB) among the red, green, and blue tone values of the RGB signal (RGB) of the pixel of the red, green, and blue colors to be a grayscale value of the pixel.
HUE CHANGING COLOR GAMUT MAPPING
An aspect of present principles is directed to methods and systems for gamut mapping colors from a either a source color gamut or a content color gamut towards a target color gamut. A source hue of the source specific colors and a source hue of the content specific colors is changed towards a target hue of the corresponding target specific colors. Color gamut mapping is performed for the source colors of either the whole source color gamut or the content color gamut towards the target color gamut based on the mapped specific colors. The specific colors are selected from primary colors, secondary colors, a group of primary colors and secondary colors.
MACHINE LEARNING COLOR SCIENCE CONVERSION
Techniques are disclosed for converting image frames from one color space to another while predicting artistic choices that a director, colorist, or others would make. In one configuration, a color conversion application receives image frames, an indication of color spaces to convert between, and metadata associated with the image frames and/or regions therein. The conversion application determines a global, base color conversion for the image frames using a predefined color space transformation. Then, the conversion application (optionally) extracts image regions depicting objects of interest in the image frames, after which the color conversion application processes each of the extracted image regions and the remaining image frames (after the extracted regions have been removed) using one or more functions determined using machine learning. The processed extracted regions and remainders of the image frames are then combined by the color conversion application for output.
Image cataloger based on gridded color histogram analysis
Embodiments of the present invention disclose a method, computer program product, and system for cataloging images based on a gridded color histogram analysis. The computer accesses an image gallery specified by a user, wherein the image gallery is at least one of an image gallery stored on a user computing device, an image gallery stored on a user account at a third-party image storage, or an image gallery searched on the web. The computer receives a request to search the image gallery specified by the user. The computer performs a search of the image gallery, wherein the search is using a color based histogram algorithm based on a user input. The computer transmits a cataloged and sorted image gallery to the user computing device to be displayed.
Image Processing Device Generating Print Data Using Profile Corresponding to Printing Direction
In an image processing device, a controller is configured to perform: selecting; generating; and outputting. The selecting selects a target partial image one by one from a plurality of partial images. The target partial image is represented by target partial image data. The generating generates partial print data for a partial print by executing an image process on the target partial image data. The partial print forms the target partial image while moving a print head in a printing direction. The partial print forms the target partial image while moving a print head in a printing direction. The image process includes a color conversion process. The color conversion process is executed on the target partial image data using one of a first profile and a second profile selected in accordance with the printing direction set for the partial print. The outputting outputs the partial print data to the printer.
Imaging pipeline processing
A method of processing data in a multi-stage imaging pipeline, the method comprising, at each stage of the multi-stage imaging pipeline, identifying a plurality of encoding values represented in received input data in a given encoding space for the respective pipeline stage, the identified plurality of encoding values comprising a subset of encoded values which are capable of being represented in the given encoding space, generating a list of encoding indices corresponding to the identified plurality of encoded values in the given encoding space, representing the encodings of one or more entities of the received input data using the generated list of encoding indices, and outputting the represented encodings of the one or more entities to the next stage of the multi-stage imaging pipeline.
Color learning
A computing device, programmed to: acquire a color image and transform the color image into a color-component map. The computer can be further programmed to process the color-component map to detect a traffic sign by determining spatial coincidence and determining temporal consistency between the color-component map and the traffic sign.
ADAPTIVE COLOR TRANSFORMATION TO AID COMPUTER VISION
System and techniques for adaptive color transformation to aid computer vision are described herein. Colors from an image are mapped into a multi-dimensional space to create a distribution of colors in the image. A line can be fit to the distribution. Here, the line includes an angle relative to a coordinate system of the multi-dimensional space. A transformation to colors can then be applied to the image based on the angle of the line. The transformation producing a reduced image where a color complexity of the original image is reduced.
Apparatus, method, and storage medium for performing color reduction processing
An apparatus includes a reduction unit configured to perform color reduction processing for quantizing a color in the generated image data, a change unit configured to change, in a case where brightness of an edge pixel indicating an edge portion in an image based on the image data with the color quantized is equal to or higher than a threshold value, a pixel value of the edge pixel to a pixel value of a color of a pixel having highest brightness among pixels surrounding the edge pixel, and change, in a case where the brightness of the edge pixel is lower than the threshold value, the pixel value of the edge pixel to a pixel value of a color of a pixel having lowest brightness among the pixels surrounding the edge pixel.
Image recognition method and apparatus, image preprocessing apparatus, and method of training neural network
A method includes obtaining a color transformation matrix that removes color distortion of an original color histogram of a target color space for an input image of an original color space; obtaining a color transformation image of the original color space from which color distortion of the input image is removed using the color transformation matrix; and obtaining a space transformation image with a minimum target loss value between an output vector of a neural network for one of candidate images and each of a plurality of candidate class vectors of the input image, the candidate images being spaced apart from the color transformation image of the original color space by a distance less than a threshold.