Image processing device, image processing method and medium
    3.
    发明授权
    Image processing device, image processing method and medium 有权
    图像处理装置,图像处理方法和介质

    公开(公告)号:US09542725B2

    公开(公告)日:2017-01-10

    申请号:US14647531

    申请日:2013-11-28

    CPC classification number: G06T3/4053 H04N1/407

    Abstract: An image processing device according to the present invention includes: a weight calculation unit that determines an area where a feature value of an input image is saved, based on a gradient of a feature value of a pixel of the input image and a direction of the gradient, and calculates a weight for reducing a regularization constraint that is a constraint based on regularization of image processing in the area where the feature value is saved; a regularization term calculation unit that calculates a regularization constraint of a high resolution image restored based on the input image by using the weight; a reconstruction constraint calculation unit that calculates a reconstruction constraint that is a constraint based on reconstruction of the high resolution image; and an image restoring unit that restores the high resolution image from the input image based on the regularization constraint and the reconstruction constraint.

    Abstract translation: 根据本发明的图像处理装置包括:权重计算单元,其基于输入图像的像素的特征值的梯度和所述输入图像的方向来确定输入图像的特征值被保存的区域 并且计算用于减少作为基于在保存特征值的区域中的图像处理的正则化的约束的正则化约束的权重; 正则化项计算单元,其通过使用所述权重来计算基于所述输入图像而恢复的高分辨率图像的正则化约束; 重建约束计算单元,其基于所述高分辨率图像的重建来计算作为约束的重建约束; 以及图像恢复单元,其基于正则化约束和重建约束从输入图像恢复高分辨率图像。

    Image processing device, image processing method and medium
    4.
    发明授权
    Image processing device, image processing method and medium 有权
    图像处理装置,图像处理方法和介质

    公开(公告)号:US09508025B2

    公开(公告)日:2016-11-29

    申请号:US14440382

    申请日:2013-11-05

    CPC classification number: G06K9/627 G06T3/4053 G06T5/003

    Abstract: An image processing device according to the present invention includes: a patch generation unit which generates an input patch used for comparison on the basis of an input image; a modification parameter estimation unit which estimates a parameter used in blurred modification on the basis of the input image; a blurred image generation unit which generates a blurred image on the basis of a learning image by using the parameter; a patch pair generation unit which generates a patch pair used to compose a restoration image on the basis of the blurred image and the learning image; a selection unit which selects a patch pair used to compose the restoration image on the basis of the input patch; and a composition unit which composes the restoration image on the basis of the patch pair selected by the selection unit.

    Abstract translation: 根据本发明的图像处理装置包括:片段生成单元,其基于输入图像生成用于比较的输入片段; 修改参数估计单元,其基于输入图像估计在模糊修改中使用的参数; 模糊图像生成单元,其通过使用所述参数来生成基于学习图像的模糊图像; 补丁对生成单元,其基于模糊图像和学习图像生成用于构成恢复图像的补丁对; 选择单元,其基于输入补丁选择用于构成恢复图像的补丁对; 以及基于由选择单元选择的补丁对构成恢复图像的合成单元。

    IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD AND MEDIUM
    5.
    发明申请
    IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD AND MEDIUM 有权
    图像处理装置,图像处理方法和介质

    公开(公告)号:US20150302273A1

    公开(公告)日:2015-10-22

    申请号:US14440382

    申请日:2013-11-05

    CPC classification number: G06K9/627 G06T3/4053 G06T5/003

    Abstract: An image processing device according to the present invention includes: a patch generation unit which generates an input patch used for comparison on the basis of an input image; a modification parameter estimation unit which estimates a parameter used in blurred modification on the basis of the input image; a blurred image generation unit which generates a blurred image on the basis of a learning image by using the parameter; a patch pair generation unit which generates a patch pair used to compose a restoration image on the basis of the blurred image and the learning image; a selection unit which selects a patch pair used to compose the restoration image on the basis of the input patch; and a composition unit which composes the restoration image on the basis of the patch pair selected by the selection unit.

    Abstract translation: 根据本发明的图像处理装置包括:片段生成单元,其基于输入图像生成用于比较的输入片段; 修改参数估计单元,其基于输入图像估计在模糊修改中使用的参数; 模糊图像生成单元,其通过使用所述参数来生成基于学习图像的模糊图像; 补丁对生成单元,其基于模糊图像和学习图像生成用于构成恢复图像的补丁对; 选择单元,其基于输入补丁选择用于构成恢复图像的补丁对; 以及基于由选择单元选择的补丁对构成恢复图像的合成单元。

    Image Processing System and Image Processing Method
    6.
    发明申请
    Image Processing System and Image Processing Method 有权
    图像处理系统和图像处理方法

    公开(公告)号:US20150117762A1

    公开(公告)日:2015-04-30

    申请号:US14361099

    申请日:2012-12-10

    Abstract: Provided is an image processing device that can bring about the sufficient resemblance between an original image and a restored image obtained corresponding to a low resolution input image. The image processing device includes a means that uses a dictionary for storing data associating deteriorated patches which are from a deteriorated image formed by deteriorating a prescribed image, and restoration patches which are from the prescribed image, and calculates, as a degree-of-similarity between plural input patches generated by dividing an input image and the deteriorated patches, a weighted degree-of-similarity between weighted deteriorated patches and weighted input patches, in which forms of the deteriorated patches and the input patches are reconfigured using a patch weight which is continuous weighting; a means that selects, on the basis of the weighted degree-of-similarity, a restoration patch for each input patch; and a means that combines the restoration patches to generate a restored image.

    Abstract translation: 提供了一种图像处理装置,其能够在原始图像和对应于低分辨率输入图像获得的恢复图像之间产生足够的相似性。 图像处理装置包括使用字典来存储关联来自由恶化规定图像形成的劣化图像的劣化斑块的数据和来自规定图像的恢复斑块的数据,并计算为相似度 在通过分割输入图像和劣化斑块生成的多个输入片段之间,加权劣化斑块和加权输入片段之间的加权相似度,其中使用补丁权重来重新配置劣化片段和输入片段的形式, 连续加权 基于加权的相似度来选择每个输入补丁的恢复补丁的装置; 并且是组合恢复补丁以生成恢复的图像的手段。

    IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD AND COMPUTER READABLE MEDIUM
    7.
    发明申请
    IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD AND COMPUTER READABLE MEDIUM 有权
    图像处理装置,图像处理方法和计算机可读介质

    公开(公告)号:US20140334720A1

    公开(公告)日:2014-11-13

    申请号:US14364834

    申请日:2012-12-10

    Abstract: The present invention generates a highly-accurate restored image while reducing computation costs by obtaining a similar effect to when the adjacent similarity of restoration patches is taken into consideration.This image processing device is provided with: a provisional restoration image generation means that uses a dictionary for storing at least two sets of data having associated therein a blurred patch and a restoration patch, and that generates a provisional restoration image from restoration patches selected on the basis of a value indicating the degree of similarity between blurred patches and a plurality of input patches generated by partitioning an externally-received input image; a provisional patch generation means that generates provisional patches by partitioning the provisional restoration image; and a restoration means that generates a restored image from restoration patches selected on the basis of the combined value of a value indicating the degree of similarity between the input patches and the blurred patches, and a value indicating the degree of similarity between the provisional patches and the restoration patches.

    Abstract translation: 本发明通过获得与考虑恢复补片的相邻相似度时相似的效果,同时降低计算成本,生成高精度的恢复图像。 该图像处理装置具有:临时恢复图像生成单元,其使用字典来存储与其相关联的模糊补丁和恢复补丁的至少两组数据,并且从恢复补丁选择的恢复补丁生成临时恢复图像 指示通过划分外部接收的输入图像而生成的模糊贴片与多个输入贴片之间的相似度的值的基础; 临时补丁生成装置,其通过分割临时恢复图像来生成临时补丁; 以及恢复装置,其根据表示输入补丁和模糊补丁之间的相似程度的值的组合值选择的恢复补丁生成恢复图像,以及指示临时补丁与临时补丁之间的相似程度的值 恢复补丁。

    Image processing system
    8.
    发明授权

    公开(公告)号:US09747675B2

    公开(公告)日:2017-08-29

    申请号:US15036231

    申请日:2014-10-17

    Abstract: Provided is an information processing system configured to: receive a plurality of images; select a standard image; search, in extracting partial images for complementing a too bright region/too dark region in the standard image from a reference images, using correction images obtained by subjecting each of the images to multivalued processing for each division of luminance components, for regions having matching shapes of respective regions included in the correction image of the standard image and the correction images of the other images; and complement image portions corresponding to the too bright region and/or too dark region in the correction image of the standard image using image portions, which are matching regions and correspond to appropriately bright regions, to thereby generate a synthetic image. Each image is dividable into at least three values: a too bright region, an appropriately bright region, and a too dark region, and has a relationship in which a boundary luminance between the too bright region and the appropriately bright region aligns with a boundary luminance between the appropriately bright region and the too dark region in a darker image having an adjacency relationship therewith.

Patent Agency Ranking