An image processing apparatus comprises: a first obtainment unit configured to obtain HDR data which represents a high-dynamic range (HDR) image; a second obtainment unit configured to obtain print information to perform printing based on the HDR data obtained by the first obtainment unit; a setting unit configured to set luminance information to be a target of the HDR data obtained by the first obtainment unit; and a conversion unit configured to convert a dynamic range of luminance of the HDR data, which has been obtained by the first obtainment unit and has been set by the setting unit with the luminance information to be the target, into a dynamic range by which printing is to be performed based on the print information obtained by the second obtainment unit.

Example embodiments allow for training of encoders (e.g., artificial neural networks (ANNs)) to facilitate dithering of images that have been subject to quantization in order to reduce the number of colors and/or size of the images. Such a trained encoder generates a dithering image from an input quantized image that can be combined, by addition or by some other process, with the quantized image to result in a dithered output image that exhibits reduced banding or is otherwise aesthetically improved relative to the un-dithered quantized image. The use of a trained encoder to facilitate dithering of quantized images allows the dithering to be performed in a known period of time using a known amount of memory, in contrast to alternative iterative dithering methods. Additionally, the trained encoder can be differentiable, allowing it to be part of a deep learning image processing pipeline or other machine learning pipeline.

In an example, a method includes receiving, at a processor, a plurality of property parameter sets representing attainable property combinations in additive manufacturing and being associated with print material description. A constraint of a first property of the property parameter sets may also be received and a hull of a property mapping resource for use in determining additive manufacturing instructions for generating an object in which the first property meets the received constraint may be determined.

Example method includes: transmitting a plurality of probe images from an IoT device at an edge network to a server hosting a target DNN, wherein the plurality of images are injected with a limited amount of noise to probe sensitivities of the target DNN to the red, green, and blue colors; receiving a feedback comprising a plurality of DCT coefficients unique to target DNN from the server hosting the target DNN; computing a plurality of color conversion weights based on the feedback received from the server; converting a set of real-time images from RGB color space to YUV color space using the plurality of color conversion weights unique to the target DNN; compressing the set of real-time images using a quantization table unique to the target DNN by the IoT device; and transmitting the compressed set of real-time images to the server hosting the target DNN for DNN inferences.

A universal color coding system, and method of analyzing objects with multiple attributes using the color coding system. The color coding system includes a color mapper arranged to map a plurality of colors with a plurality of numerical codes, wherein the each of the plurality of numerical codes is a unique integer determined based on a combination of prime numbers; wherein each of the plurality of numerical codes is arranged to represent a unique color in color space wherein each of the prime numbers represents a respective basic color of the color space; and wherein the plurality of numerical codes are integers calculated based on addition and multiplication of a plurality of prime numbers.

The present invention is related to video coding and decoding, in particular HEVC RExt that define a palette coding mode dedicated to the coding of screen contents. In improved palette coding modes according to the invention, when building a palette, each time a new pixel is added to the class a palette entry defines, the palette entry is modified to take the means value of the pixels belonging to such class. In other improved palette coding modes, a built palette is post-processed to substitute a palette entry with a close entry of a palette predictor PRED. In yet other embodiments, palette coding modes having different threshold values to drive the building of their respective palettes are successively tested to use the best one in terms of rate-distortion criterion.

An image processing apparatus includes an input unit for inputting an image, a division unit for dividing the inputted image into a plurality of divided regions, an obtaining unit for obtaining a feature amount of the image for each of the divided regions, a generation unit for generating a compression curve for each divided region, and a compression unit for generating an output image by performing compression of a dynamic range using the compression curve for each of the divided regions. The generation unit generates the compression curve for each of the divided regions so that a slope of the compression curve for each of the divided regions matches in a range from a luminance of a dark region of the image to a luminance of a predetermined brightness.

A method, apparatus, and non-transitory computer readable medium for color reduction based on image segmentation are described. The method, apparatus, and non-transitory computer readable medium may provide for segmenting an input image into a plurality of regions, assigning a weight to each region, identifying one or more colors for each of the regions, selecting a color palette based on the one or more colors for each of the regions and the corresponding weight for each of the regions, and performing a color reduction on the input image using the selected color palette to produce a color reduced image. The weight assigned to each region may depend on factors including relevance, prominence, focus, position, or any combination thereof.

Provided is an image processing apparatus for increasing the speed of pixel processing of index colors. A LUT reading unit reads a LUT for converting index colors to pixel values for each plane. A first storage unit stores the look up table read by the LUT reading unit. A plane LUT copying unit acquires pixel values corresponding to each place from the look up table stored in the first storage unit. A second storage unit stores the pixel values acquired by the plane LUT copying unit. A pixel processing unit performs image data processing using the pixel values stored in the second storage unit.

Example method includes: transmitting a plurality of probe images from an IoT device at an edge network to a server hosting a target DNN, wherein the plurality of images are injected with a limited amount of noise to probe sensitivities of the target DNN to the red, green, and blue colors; receiving a feedback comprising a plurality of DCT coefficients unique to target DNN from the server hosting the target DNN; computing a plurality of color conversion weights based on the feedback received from the server; converting a set of real-time images from RGB color space to YUV color space using the plurality of color conversion weights unique to the target DNN; compressing the set of real-time images using a quantization table unique to the target DNN by the IoT device; and transmitting the compressed set of real-time images to the server hosting the target DNN for DNN inferences.