Methods and systems are provided for generating harmonized images for input composite images. A neural network system can be trained, where the training includes training a neural network that generates harmonized images for input composite images. This training is performed based on a comparison of a training harmonized image and a reference image, where the reference image is modified to generate a training input composite image used to generate the training harmonized image. In addition, a mask of a region can be input to limit the area of the input image that is to be modified. Such a trained neural network system can be used to input a composite image and mask pair for which the trained system will output a harmonized image.

An image processing apparatus includes a conversion unit configured to convert an image in a first color space into an image in a second color space in such a manner that the image in the second color space has a bit depth smaller than a bit depth of the image in the first color space, a first recognition unit configured to perform first recognition processing using the image in the second color space, and a second recognition unit configured to perform second recognition processing on an image area that is determined to be the image area in which the second recognition processing is performed on the image in the first color space based on a result of the first recognition processing.

A video encoding and decoding system that implements an adaptive transfer function method internally within the codec for signal representation. A focus dynamic range representing an effective dynamic range of the human visual system may be dynamically determined for each scene, sequence, frame, or region of input video. The video data may be cropped and quantized into the bit depth of the codec according to a transfer function for encoding within the codec. The transfer function may be the same as the transfer function of the input video data or may be a transfer function internal to the codec. The encoded video data may be decoded and expanded into the dynamic range of display(s). The adaptive transfer function method enables the codec to use fewer bits for the internal representation of the signal while still representing the entire dynamic range of the signal in output.

A method of gamut mapping and color gamut mapping apparatus comprises: acquiring the Lab value of the color point in the original color gamut; and determining the color point in the original color gamut relative to the coordinate location in a hue plane based on the Lab value; and determining the mapping target gamut of the color point based on the coordinate location; If a color point is located outside the mapping target area, it determining the first intersection point of the line connecting the color point and the maximum brightness and the borderline of the mapping target color gamut and the second intersection point of the color point relative to the borderline of the mapping target gamut, and finally according to the preset adjustment parameter, the mapping point being determined on the borderline of the mapping target color gamut relative to the color point.

A method includes receiving information specifying a color gamut. The color gamut corresponds to a range of colors producible by an output device. The method further includes receiving a first indication of a first color associated with a first point in a geometrical representation of the color gamut in a three-dimensional (3D) color space. The method further includes generating, based on the first color, a second indication of a second color that is included in the color gamut. The second color is associated with a second point in the 3D color space. The second point is identified based on a particular value of data associated with a plurality of distances between the first point and a subset of points of the geometrical representation. The subset of points includes more than one and fewer than all points of the geometrical representation.

The present disclosure generally relates to a method and device of converting a HDR version of a picture to a SDR version of this picture. The method is characterized in that it converts the HDR version to the SDR version of the picture according to: a first indicator that indicates the presence of color mapping parameters; a second indicator that indicates whether a device is configured to convert the HDR version to the SDR version of the picture by taking into account said color mapping parameters; and a third indicator that indicates whether converting without taking into account said color mapping parameters is inhibited.

A method of manufacturing a wood stain display sample includes optically scanning a wood sample including a wood stain with a computing device to generate a digital image of the wood stain. The method includes altering the digital image by adjusting a color of one or more portions of the digital image to correlate the color of the one or more portions to a color gamut of a xerographic printing process to form a color-adjusted digital image. The method includes printing the color-adjusted digital image to a substrate using a xerographic printing process to form the wood stain display sample. The printing includes printing an underlay toner to the substrate. The underlay toner includes a white or a transparent color. The printing includes printing a yellow, magenta, cyan, and black toner over the underlay toner. The printing includes printing an overlay toner to the black toner.

Web server based color management hosted by a web server is provided enabling a production device to produce a print job with a similar color appearance as a reference device. The web server receives a production device color management profile and a reference device color management profile. The web server creates an output color management profile based on the color management profile of the production device and the color management profile of the reference device. The output color management profile maps device-independent color values associated in the color management profile of the reference device to device-specific color values for colors reproducible by the production device.

A profile information display apparatus includes a database section in which a plurality of output profiles including information concerning association of a coordinate value in a first color space and a coordinate value in a second color space are accumulated, a color-value receiving section configured to receive an input of a color value indicating the coordinate value in the first color space, a color-reproduction determining section configured to determine, concerning each of the plurality of output profiles, whether the output profile is capable of reproducing the color value, a display section configured to display information, and a display control section configured to cause, based on a result of the determination of the color-reproduction determining section, the display section to display setting information concerning one or more output profiles selected from the plurality of output profiles.

Techniques for interactively determining/visualizing the color content of a source image and how the corresponding image data is mapped to device colors are described herein. For example, the color content of a digital image can be converted between different color spaces to identify gamut limitations of an output device (e.g., a printing assembly), discover color(s) that cannot be accurately reproduced, etc. Color space conversions enable the transformation of the color content of the digital image from device-specific colorants to a device-independent representation (and vice versa). In some embodiments, these transformations are facilitated using lookup tables that are implemented in graphical processing unit-resident memory.