Read image data is divided into a plurality of regions, and a histogram is generated and edges are counted for each region. Blank page detection is performed based on a variance value computed from the histogram of each region. Also, the variance between regions is computed from the edge count of each region, and blank page detection is performed according to the amount of variance. It is then determined whether the document is blank or content based on the result of detection by histogram and the result of detection by edge count.

A first concentration range, which is a concentration range of a region of interest, and an output concentration range are determined in an input image. A compression table for compressing a dynamic range of the input image is generated on the basis of the first concentration range and the output concentration range. The first concentration range is changed at a predetermined ratio with respect to the changed output concentration range to determine a second concentration range. A new compression table is generated on the basis of the changed output concentration range and the second concentration range. The dynamic range of the input image is compressed using the new compression table.

A system accesses an image with each pixel of the image having luminance values each representative of a color component of the pixel. The system generates a first histogram for aggregate luminance values of the image, and accesses a target histogram for the image representative of a desired global image contrast. The system computes a transfer function based on the first histogram and the target histogram such that when the transfer function is applied, a histogram of the modified aggregate luminance values is within a threshold similarity of the target histogram. The system modifies the image by applying the transfer function to the luminance values of the image to produce a tone mapped image, and outputs the modified image.

Based on a multi-step process, an automatic hair segmentation method and system are disclosed. By extracting various information components from an image, including background color, face position, hair color, skin color, and skin mask, a heuristic-based method is created for the detection and segmentation of hair that can detect hair with an accuracy of approximately 75% and with a false hair overestimation error of 34%. Furthermore, it is shown that down sampling the image down to a face width of 25 px results in a 73% reduction in computation time with insignificant change in detection accuracy.

An image processing apparatus according to this embodiment performs, based on a job setting, conversion of a pixel value of a partial region in an input original image into a predetermined value on image data of the original image, as needed. Subsequently, this image processing apparatus generates a histogram representing the density signal distribution of the image data of the original image or the converted image data. Note that if the above-described conversion is performed, this image processing apparatus corrects the generated histogram by subtracting, from a count of the predetermined number of the generated histogram, the number of sampling points counted in the above-described partial region when the histogram is generated.

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.

A method, device and medium for enhancing saturation are provided. The method includes: obtaining image feature information of an image; identifying a type of the image according to the image feature information; selecting a saturation enhancement mode corresponding to the type of the image, and enhancing the saturation of the image using the saturation enhancement mode.

An image processing apparatus includes a degree-of-degradation detector, a correction coefficient calculator and an adaptive gradation correction unit. The degree-of-degradation detector detects a degree of degradation of image quality for each of areas included in image data and having predetermined size. The correction coefficient calculator calculates a correction coefficient for gradation correction, for each of the areas of the image data. The adaptive gradation correction unit performs adaptive gradation correction appropriate to the degree of degradation of the image data, based on the degree of degradation detected by the degree-of-degradation detector and the correction coefficient calculated by the correction coefficient calculator.

A data conversion device includes a processor configured to acquire image data output from a first line sensor, and convert pixel values included in the image data output from the first line sensor, in accordance with correspondence relation data in which a correspondence relation of pixel values is set based on a sensitivity difference for a spectral characteristic between the first line sensor and a second line sensor that is different from the first line sensor.

The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement an image filter for enhancing light text and removing document shadows. In particular embodiments, the disclosed systems use a modified adaptive thresholding approach the relies on image gradients to efficiently guide the thresholding process. In addition, the disclosed systems use a machine-learning model to generate a document shadow map. The document shadow map can include text reflections. Accordingly, the disclosed systems remove text reflections from the document shadow map (e.g., by using an interpolated shadow intensity value of neighboring shadow map pixels). In turn, the disclosed systems use the document text mask and the document shadow map cleaned of text reflections to remove shadows from the digital image. Further, the disclosed systems enhance text in the shadow-removed digital image based on contrast stretching.