公开(公告)号：US20150302566A1

公开(公告)日：2015-10-22

申请号：US14648830

申请日：2013-12-05

Applicant: NEC CORPORATION

Inventor： Takashi SHIBATA ,  Akihiko IKETANI ,  Shuji SENDA

IPC: G06T5/50 ,  G06K9/62 ,  G06T11/60 ,  G06K9/66

CPC classification number: G06T5/50 ,  G06K9/40 ,  G06K9/6226 ,  G06K9/6255 ,  G06K9/6272 ,  G06K9/66 ,  G06K2209/01 ,  G06T3/4053 ,  G06T5/001 ,  G06T11/60 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20221

Abstract: The present invention provides an image processing device whereby the probability of outputting a restored image which accurately corresponds to an original image which is included in a low-quality input image is improved. This image processing device comprises: an image group generating means for generating, from the input image, using a dictionary which stores a plurality of patch pairs wherein a degradation patch which is a patch of a degraded image wherein a prescribed image is degraded is associated with a restoration patch which is a patch of this prescribed image, a plurality of restored image candidates including a plurality of different instances of content which have a possibility of being the original content of the input image; and an image selection presentation means for clustering the generated plurality of restored image candidates, and selecting and outputting an image candidate on the basis of the result of this clustering.

Abstract translation: 本发明提供了一种图像处理装置，由此提高了输出与包含在低质量输入图像中的原始图像精确对应的恢复图像的概率。 该图像处理装置包括：图像组生成装置，用于从输入图像生成存储多个补丁对的字典，其中，其中规定图像劣化的劣化图像的补丁与劣化补丁相关联 恢复补丁，其是该规定图像的补丁;多个恢复图像候选，其包括具有作为输入图像的原始内容的可能性的多个不同内容实例; 以及图像选择呈现装置，用于对生成的多个恢复的图像候选进行聚类，并且基于该聚类的结果来选择和输出图像候选。

公开(公告)号：US20160098852A1

公开(公告)日：2016-04-07

申请号：US14893484

申请日：2014-04-22

Applicant: TOKYO INSTITUTE OF TECHNOLOGY ,  NEC CORPORATION

Inventor： Shuji SENDA ,  Akihiko IKETANI ,  Takashi SHIBATA ,  Masatoshi OKUTOMI ,  Masayuki TANAKA

IPC: G06T11/60 ,  G06K9/46 ,  G06K9/62

CPC classification number: G06T11/60 ,  G06K9/00677 ,  G06K9/00771 ,  G06K9/46 ,  G06K9/6215 ,  G06K9/6293 ,  G06K2009/4666 ,  G06T2200/28 ,  G06T2207/20021 ,  G06T2207/20024 ,  H04N5/247 ,  H04N5/262

Abstract: A basis image is converted into a more functional image by image synthesis technology using a number of imaging devices arranged independently of each other. A multocular imaging system is provided with a plurality of imaging parts that can be arranged independently of each other, a similar component search part operable to acquire a basis image outputted from at least one imaging part of the plurality of imaging parts and a reference image outputted from another imaging part of the plurality of imaging parts and to search a similar component included in the reference image for each of components included in the basis image, and an image synthesis part operable to perform a synthesis process on at least one component included in the basis image into a desired image with reference to the similar component extracted by the similar component search part and to output the desired image as a synthesis image.

Abstract translation: 通过使用彼此独立排列的多个成像装置的图像合成技术将基础图像转换为更多功能的图像。 多个成像系统具有能够相互独立排列的多个成像部，具有可以从多个成像部的至少一个成像部输出的基础图像和输出的基准图像的相似成分检索部， 从所述多个成像部件的另一成像部分中搜索包括在所述基础图像中的每个部件的所述参考图像中的类似部件，以及可操作以对包括在所述基础图像中的至少一个部件执行合成处理的图像合成部分 参考由相似分量搜索部分提取的相似分量并将所需图像作为合成图像输出到所需图像中。

公开(公告)号：US20160292835A1

公开(公告)日：2016-10-06

申请号：US15036231

申请日：2014-10-17

Applicant: NEC CORPORATION ,  TOKYO INSTITUTE OF TECHNNOLOGY

Inventor： Takashi SHIBATA ,  Shuji SENDA ,  Masayuki TANAKA ,  Masatoshi OKUTOMI ,  Takehito HAYAMI

IPC: G06T5/00 ,  G06T5/50

CPC classification number: G06T5/009 ,  G06T5/008 ,  G06T5/50 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10144 ,  G06T2207/20208 ,  G06T2207/20221 ,  H04N1/3871 ,  H04N1/4072 ,  H04N5/265

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.

Abstract translation: 提供了一种信息处理系统，被配置为：接收多个图像; 选择标准图像; 搜索从参考图像中提取部分图像以补充标准图像中的太亮区域/太暗区域，使用通过对每个图像进行多值处理而获得的校正图像对于每个亮度分量的分割，对于具有匹配形状的区域 包括在标准图像的校正图像中的各个区域和其他图像的校正图像; 并且使用作为匹配区域的图像部分并对应于适当的亮区域来对应于标准图像的校正图像中的太亮区域和/或太暗区域的图像部分，从而生成合成图像。 每个图像可分为至少三个值：太亮区域，适当亮区域和太暗区域，并且具有其中太亮区域和适当亮区域之间的边界亮度与边界亮度对齐的关系 在与其邻接关系的较暗图像中的适当亮区域和太暗区域之间。

公开(公告)号：US20160189357A1

公开(公告)日：2016-06-30

申请号：US14911556

申请日：2014-07-18

Applicant: NEC Corporation

Inventor： Takashi SHIBATA ,  Akihiko IKETANI ,  Shuji SENDA

IPC: G06T7/00 ,  G06K9/62 ,  G06T3/40 ,  G06K9/48

CPC classification number: G06T7/0002 ,  G06K9/40 ,  G06K9/481 ,  G06K9/6215 ,  G06K9/6255 ,  G06K9/6857 ,  G06T3/4053 ,  G06T5/001 ,  G06T2207/20081

Abstract: The present invention provides an information processing device in which a degradation process of an input image is accurately estimated and a dictionary necessary for generating a desired restored image from the input image can be obtained. The information processing device is provided with: an image acquisition means that acquires a plurality of study images and an input image; and an estimation means that, on the basis of similarity between an arbitrary region of the input image and each of a plurality of degradation images in a case where regions of the study images corresponding to the arbitrary region are degraded on the basis of each of the plurality of degradation processes, outputs an estimated degradation process corresponding to the degradation process corresponding to the region of the input image.

Abstract translation: 本发明提供了一种信息处理装置，其中准确地估计输入图像的劣化处理，并且可以获得从输入图像生成期望的恢复图像所需的字典。 该信息处理装置具备：获取多个研究图像和输入图像的图像获取单元; 并且估计装置，基于在与任意区域相对应的研究图像的区域基于每个的任意区域劣化的情况下，输入图像的任意区域和多个退化图像中的每一个之间的相似度 多个退化处理，输出与对应于输入图像的区域的退化处理对应的估计退化处理。