Canon Kabushiki Kaisha

Atsushi Takahama

Yoshitaka Sasaki

Kazuhiro Yahata

Toru Kokura

An image processing apparatus includes an acquisition unit configured to acquire training image data, an extraction unit configured to learn the training image data and extract first difficult image data that is difficult to learn from a result of the learning, a generation unit configured to generate student image data by mosaicking the first difficult image data, and a training unit configured to generate a network parameter obtained by re-learning a pair of the first difficult image data and the student image data. The training unit repeats the re-learning by generating a plurality of times second difficult image data different from the first difficult image data.

Image processing apparatus, image processing method, and storage medium

A noise reduction unit reduces color noise of an input image to generate a noise-reduced image. A first generation unit generates a color difference signal from the noise-reduced image. A reduction processing unit generates hierarchical images including at least two or more reduced images from the noise-reduced image. A second generation unit generates coloring-suppressed color difference signals from the reduced images. A combining unit combines the color difference signal generated by the first generation unit with each of the color difference signals generated by the second generation unit. The second generation unit selects one of the color difference signals of the reduced images for each pixel based on magnitude of each of the color difference signals of the reduced images, to generate the coloring-suppressed color difference signals.

Image processing apparatus, method and storage medium for reducing color noise and false color

A set of patches including a patch of interest formed of pixels relative to a pixel of interest and a similar patch thereof is acquired. A noise amount parameter corresponding to each pixel in the patch of interest is estimated based on a pixel value of the each pixel in the patch of interest. A covariance matrix corresponding to the set of patches on the assumption that each pixel has a uniform noise amount parameter is calculated based on the set of patches. Based on the covariance matrix and the noise amount parameter, a covariance matrix corresponding to the noise amount parameter of the each pixel is estimated. Using the estimated covariance matrix, a patch in which noise of at least the patch of interest among the patches included in the set of patches is reduced is generated.

Image processing apparatus, image processing method, and non-transitory computer-readable storage medium

An image processing apparatus includes a processing unit to perform noise reduction processing on image data and an output unit to output noise-reduced output image data. The processing unit determines a weight for a reference pixel based on a target area including a target pixel and a reference area including the reference pixel and sets, as a pixel value of the target pixel on which processed noise reduction processing has been executed, a value calculated using reference pixels and a weight corresponding to each of the reference pixels. The size of the target area equals to the size of the reference area. The output unit outputs, as the pixel value of the target pixel after noise reduction processing, either a first value, calculated when a first pixel group is set as the target area, or a second value, calculated when a second pixel group is set as the target area.

Image processing apparatus and image processing method that perform noise reduction processing on image data

Color noise is reduced while suppressing the occurrence of color blurring in the vicinity of an edge. An image processing apparatus including: a first determination unit configured to determine whether or not a first area consisting of a plurality of pixels including a pixel of interest is an area in a uniform color for the pixel of interest in input image data; a second determination unit configured to determine whether or not a second area, different from the first area, consisting of a plurality of pixels including the pixel of interest is an area in a uniform color; a setting unit configured to set a reference area consisting of the pixel of interest and adjacent pixels of the pixel of interest for the pixel of interest; and a first correction unit configured to correct the pixel value of the pixel of interest to a value for which noise has been reduced based on the pixel value of the pixel included in the reference area.

Image processing apparatus, image processing method, and storage medium for reducing color noise in an image

An image processing apparatus processes image data. A first correction unit (i) corrects a pixel value of a target pixel in the image data based on a first similarity determined by comparing pixels included in a first target pixel group including the target pixel with pixels included in a first reference pixel group including a reference pixel, and (ii) produces a first corrected pixel value of the target pixel. A second correction unit (i) corrects the pixel value of the target pixel based on a second similarity determined by comparing pixels included in a second target pixel group including the target pixel with pixels included in a second reference pixel group including a reference pixel, and (ii) produces a second corrected pixel value. An output unit obtains corrected image data by using the first and second corrected pixel values based on the first similarity or the second similarity.

Image processing apparatus and image processing method

An image processing apparatus executes image processing on image data obtained by forming an image on an image pickup element. The image processing apparatus includes an obtaining unit configured to obtain a pixel in the image data corresponding to a specific position in the image pickup element as a specific pixel, a determination unit configured to determine a target region including a target pixel and a reference region including a reference pixel which are used for determining a degree of similarity between the target pixel and the reference pixel in accordance with the specific pixel obtained by the obtaining unit, and a calculation unit configured to calculate a degree of similarity between the target pixel and the reference pixel by comparing the target region and the reference region determined by the determination unit.

Growing community of inventors

Kawasaki, Japan

Atsushi Takahama