A controller 60 of an image reading device 1 acquires a scanned image by reading a document. An image processor 30 generates an output image by applying to the acquired scanned image different image processes based on whether or not specific pixels, which are pixels with a pixel value greater than a white reference value, are contained in the scanned image.

A non-transitory computer-readable storage medium stores executable instructions that, when executed by a processor, cause performance of operations comprising operations to access an image captured by an image sensor, obtain a transfer function for mapping pixel values, determine a faces indication that reflects a proportion of a scene depicted in the image that includes one or more human faces, and modify the transfer function based on the faces indication. Modifying the transfer function based on the faces indication comprises adjusting a gain of the transfer function to move the gain closer to unity. The operations include to apply the transfer function to pixel values of the image to produce a tone mapped image and output the tone mapped image.

A three-dimensional image data generation system includes: an editing unit configured to edit grayscale image data in which a density level for specifying an foaming height of a thermally expandable sheet is set for each coordinate in a planar direction; and a conversion unit configured to, when the editing unit changes a size in the planar direction of an image region included in the grayscale image data, convert the density level in correspondence with a ratio of the image region between before and after the change.

An image pickup apparatus according to an embodiment includes an image pickup unit configured to take an image including an object, a shooting condition control unit configured to control a shooting condition for the image pickup unit so that no blown out highlight occurs in a taken image taken by the image pickup unit, an object extraction unit configured to extract the object included in the taken image, a block-division unit configured to divide the taken image into a plurality of blocks according to the object extracted by the object extraction unit, a gamma correction unit configured to gamma-correct a gradation value of the taken image for each block by using a gamma value set for each block based on the object, and a boundary correction unit configured to correct the gradation value in a boundary area between adjoining blocks.

Provided is an image compression method of a digital pathology system. The image compression method is a method of compressing digital slide images having first to nth original plane images (n is a natural number greater than or equal to 2). The image compression method includes selecting a block having an optimal focal point as an optimal block from each set of blocks positioned at identical positions of the first to nth original plane images; forming one plane image as a virtual optimal plane image by combining only the optimal blocks; generating block descriptors for forming the first to nth original plane images based on the virtual optimal plane image; generating first to nth predictive plane images from the virtual optimal plane image such that the first to nth predictive plane images are out of focus and most similar to the first to nth original plane images by using location information for the blocks and the block descriptors; generating first to nth differential plane images, the first differential plane image corresponding to a difference between the first original plane image and the first predictive plane image and the nth differential plane image corresponding to a difference between the nth original plane image and the nth predictive plane image; and compressing the first to nth differential plane images.

The present disclosure relates to an image processing apparatus, an image processing method, a program, and an endoscope system capable of obtaining an image with high color discrimination. A histogram generation unit generates histograms of pixel values for an input image regarding luminance Y, saturation S, and hue H. A histogram correction unit subtracts components of the saturation, the luminance, and the hue of a portion determined to be a foreign object by a foreign object detection unit from the histograms regarding the saturation, the luminance, and the hue generated by the histogram generation unit and then weights by a value of a standard histogram. The present disclosure may be applied to the endoscope system which performs color conversion on an image input from a camera head through a scope, for example.

An image processing apparatus includes a target value calculation unit configured to calculate a target value to be output in a predetermined region in input image data based on pixel values of pixels included in the region, a distribution order determination unit configured to determine a distribution order of output values for distributing output values corresponding to the target value in the region based on a pixel value of each pixel included in the region and a threshold value in the threshold matrix corresponding to the pixel, and an output value determination unit configured to determine an output value of each pixel included in the region by allocating the target value to at least one pixel included in the region in the distribution order.

Embodiments related to local tone mapping for symbol reading. A local pixel neighborhood metric is determined for at least one raw pixel in a region-of-interest, which identifies on one or more raw pixels near the at least one raw pixel. A local mapping function is determined for the at least one raw pixel that maps the value of the raw pixel to a mapped pixel value with a mapped bit depth that is smaller than the bit depth associated with the raw image. The local mapping function is based on a value of at least one other raw pixel near the at least one raw pixel within the local pixel neighborhood metric, and at least one parameter determined based on the raw image. A mapped image is computed for the region-of-interest by applying the local mapping function to the raw image.

An apparatus and a method for mapping colors of a source image to colors of a reference image, where the apparatus is configured to match a histogram of the source image to a histogram of the reference image to generate a histogram matched image of the source image, generate a conditional probability distribution of the reference image, and detect outliers in the histogram matched image based on the conditional probability distribution.

An image processing apparatus 100 is provided with a converter 102 to convert a first color image into lightness information and color information other than the lightness information, a lightness compressor 104 to generate compressed lightness information obtained by decimating a pixel value from the lightness information, a reconverter 106 to combine the compressed lightness information and the color information to generate a second color image, an edge extractor 108 to extract an edge included in the first color image, and a pixel value changer 110 to change a pixel value at a position of the edge in the second color image while maintaining similar colors, to generate a third color image.