公开(公告)号：US08644683B2

公开(公告)日：2014-02-04

申请号：US11751107

申请日：2007-05-21

Applicant: Hirotaka Shiiyama

Inventor： Hirotaka Shiiyama

IPC: G11B27/00 ,  G11B27/034

CPC classification number: G11B27/034 ,  G11B27/10 ,  G11B27/105 ,  G11B2220/2562 ,  H04N21/8352 ,  H04N21/84 ,  H04N21/8547

Abstract: A moving image processing apparatus gives an ID to a video segment obtained by dividing moving image data, and stores information for associating a section of each video segment with the ID as video segment section information. Here, meta-data corresponding to each video segment is managed by associating the meta-data with the ID given to each video segment. In editing operations, editing in units of a video segment is performed, and an arrangement of video segment IDs is manipulated. Therefore, even if the editing is performed, there arises no inconsistency in referring to meta-data information so that it is equivalent to having the meta-data updated in synchronization with the moving image editing. Thus, it is possible to have virtual editing of the moving image automatically followed by an update of the meta-data and also alleviate a burden of reediting the meta-data of an editor.

Abstract translation: 运动图像处理装置对通过划分运动图像数据而获得的视频片段给出ID，并且存储用于将每个视频段的一部分与该ID相关联的信息作为视频段段信息。 这里，通过将元数据与给予每个视频段的ID相关联来管理对应于每个视频段的元数据。 在编辑操作中，执行以视频段为单位的编辑，并且操纵视频段ID的排列。 因此，即使执行编辑，也不会在参照元数据信息时产生不一致之处，因此等同于与移动图像编辑同步地更新元数据。 因此，可以自动进行运动图像的虚拟编辑，然后更新元数据，并且还减轻了重新编辑编辑器的元数据的负担。

公开(公告)号：US08515177B2

公开(公告)日：2013-08-20

申请号：US12552908

申请日：2009-09-02

Applicant: Masahiro Matsushita ,  Hirotaka Shiiyama ,  Hidetomo Sohma ,  Koichi Magai

Inventor： Masahiro Matsushita ,  Hirotaka Shiiyama ,  Hidetomo Sohma ,  Koichi Magai

IPC: G06K9/46

CPC classification number: G06K9/4671 ,  G06T5/002 ,  G06T5/005 ,  G06T5/009 ,  G06T5/20 ,  G06T5/40 ,  G06T2207/20012

Abstract: An image processing apparatus executes smoothing processing (reduction conversion) of an input image to acquire a smoothed image (reduced image), acquires a normalization parameter for normalization from the smoothed image, and normalizes pixel values of the input image based on the normalization parameter.

Abstract translation: 图像处理装置执行输入图像的平滑处理（缩小转换）以获得平滑图像（缩小图像），从平滑图像获取归一化参数，并根据归一化参数对输入图像的像素值进行归一化。

公开(公告)号：US08416982B2

公开(公告)日：2013-04-09

申请号：US12566562

申请日：2009-09-24

Applicant: Koichi Magai ,  Hirotaka Shiiyama ,  Hidetomo Sohma ,  Masahiro Matsushita

Inventor： Koichi Magai ,  Hirotaka Shiiyama ,  Hidetomo Sohma ,  Masahiro Matsushita

IPC: G06K9/00

CPC classification number: G06F17/30256

Abstract: An image processing method performs reduction processing on an input image to acquire a reduced image, extracts a feature point from a group of images including the input image and one or more of the reduced images, determines as a matched feature point the feature point extracted from a matching position in each of two or more images in the group of images, calculates a local feature quantity of the matched feature point determined by the determination unit, and registers the calculated local feature quantity as a local feature quantity of the input image.

Abstract translation: 图像处理方法对输入图像进行缩小处理以获取缩小图像，从包括输入图像和一个或多个缩小图像的图像组中提取特征点，将匹配的特征点确定为从 在图像组中的两个或更多个图像的每一个中的匹配位置，计算由确定单元确定的匹配特征点的局部特征量，并将所计算的局部特征量登记为输入图像的局部特征量。

公开(公告)号：US08280196B2

公开(公告)日：2012-10-02

申请号：US12764660

申请日：2010-04-21

Applicant: Koichi Magai ,  Hirotaka Shiiyama

Inventor： Koichi Magai ,  Hirotaka Shiiyama

IPC: G06K9/54 ,  G06K9/46

CPC classification number: G06K9/6212 ,  G06K9/6211 ,  G06K9/6857

Abstract: An image retrieval apparatus configured so as to enable a global feature method and a local feature method to complement each other is provided. After obtaining a retrieval result candidate using the local feature method, the image retrieval apparatus further verifies global features already registered in a database, with regard to the retrieval result candidate image. A verification position of the global features is estimated using the local features.

Abstract translation: 提供一种图像检索装置，其被配置为使得能够使全局特征方法和局部特征方法互补。 在使用局部特征方法获得检索结果候选者之后，图像检索装置进一步验证已经登记在数据库中的关于检索结果候选图像的全局特征。 使用本地功能估算全局特征的验证位置。

公开(公告)号：US08077976B2

公开(公告)日：2011-12-13

申请号：US11598026

申请日：2006-11-13

Applicant: Hirotaka Shiiyama

Inventor： Hirotaka Shiiyama

IPC: G06K9/46

CPC classification number: G06K9/2063 ,  G06K2209/01

Abstract: Of the feature amounts of respective regions on an image, a region having a feature amount which is similar to that of a region of interest on a image is specified (S1307). Of the OCR results of the respective regions on the image, a region having an OCR result which matches that of the region of interest on the image is specified (S1308). Regions corresponding to respective regions on the image of the respective regions are specified based on the layout order of the specified regions (S1311). Of the regions obtained by combining neighboring regions on the image, a region corresponding to an inclusion region that includes each specified region is specified (S1314).

Abstract translation: 在图像上的各个区域的特征量中，指定具有与图像上的感兴趣区域的特征量相似的特征量的区域（S1307）。 在图像上的相应区域的OCR结果中，指定具有与图像上的感兴趣区域的OCR结果匹配的OCR结果的区域（S1308）。 基于指定区域的布局顺序来指定对应于各个区域的图像上的各个区域的区域（S1311）。 在通过组合图像上的相邻区域获得的区域中，指定与包括每个指定区域的包含区域对应的区域（S1314）。

公开(公告)号：US20100104197A1

公开(公告)日：2010-04-29

申请号：US12603427

申请日：2009-10-21

Applicant: Hidetomo Sohma ,  Hirotaka Shiiyama ,  Masahiro Matsushita ,  Koichi Magai

Inventor： Hidetomo Sohma ,  Hirotaka Shiiyama ,  Masahiro Matsushita ,  Koichi Magai

IPC: G06K9/46 ,  G06K9/68

CPC classification number: G06K9/527 ,  G06F17/30277 ,  G06K9/4671

Abstract: An image processing apparatus reduces two input images to be compared by the predetermined number of times to generate two image groups, extracts a plurality of feature points and a local feature amount of each feature point from these image groups, and determines a combination of feature points in which local feature amounts are similar to each other, between the image groups. Then, the image processing apparatus determines a relation of a reasonable combination, assigns high weights to the reasonable combination, and calculates a similarity degree between the two input images.

Abstract translation: 图像处理装置将要比较预定次数的两个输入图像减少以生成两个图像组，从这些图像组中提取每个特征点的多个特征点和局部特征量，并且确定特征点的组合 其中局部特征量彼此相似，在图像组之间。 然后，图像处理装置确定合理组合的关系，将高权重分配给合理的组合，并计算两个输入图像之间的相似度。

公开(公告)号：US20090324075A1

公开(公告)日：2009-12-31

申请号：US11331311

申请日：2006-01-11

Applicant: Hirotaka Shiiyama

Inventor： Hirotaka Shiiyama

IPC: G06K9/00

CPC classification number: G06K9/4647 ,  G06T7/30 ,  G06T2207/20021 ,  G06T2207/20068

Abstract: The horizontal and vertical projection histograms of an image to be processed are calculated. The autocorrelation values of the calculated horizontal and vertical projection histograms are calculated, and horizontal and vertical object sizes until the autocorrelation values decrease to predetermined thresholds are calculated. The aspect ratio estimate value of the circumscribed rectangle of an object serving as a comparison region candidate in the image to be processed is calculated on the basis of the calculation results. The comparison region candidate is corrected on the basis of the aspect ratio estimate value, determining a final comparison region.

Abstract translation: 计算要处理的图像的水平和垂直投影直方图。 计算所计算的水平和垂直投影直方图的自相关值，并计算直到自相关值下降到预定阈值的水平和垂直物体尺寸。 基于计算结果计算用作待处理图像中的比较区域候补的对象的外接矩形的宽高比估计值。 基于宽高比估计值来校正比较区候选，确定最终比较区域。

公开(公告)号：US20070230807A1

公开(公告)日：2007-10-04

申请号：US11751107

申请日：2007-05-21

Applicant: Hirotaka Shiiyama

Inventor： Hirotaka Shiiyama

IPC: G06K9/36

CPC classification number: G11B27/034 ,  G11B27/10 ,  G11B27/105 ,  G11B2220/2562 ,  H04N21/8352 ,  H04N21/84 ,  H04N21/8547

Abstract: A moving image processing apparatus gives an ID to a video segment obtained by dividing moving image data, and stores information for associating a section of each video segment with the ID as video segment section information. Here, meta-data corresponding to each video segment is managed by associating the meta-data with the ID given to each video segment. In editing operations, editing in units of a video segment is performed, and an arrangement of video segment IDs is manipulated. Therefore, even if the editing is performed, there arises no inconsistency in referring to meta-data information so that it is equivalent to having the meta-data updated in synchronization with the moving image editing. Thus, it is possible to have virtual editing of the moving image automatically followed by an update of the meta-data and also alleviate a burden of reediting the meta-data of an editor.

Abstract translation: 运动图像处理装置对通过划分运动图像数据而获得的视频片段给出ID，并且存储用于将每个视频段的一部分与该ID相关联的信息作为视频段段信息。 这里，通过将元数据与给予每个视频段的ID相关联来管理对应于每个视频段的元数据。 在编辑操作中，执行以视频片段为单位的编辑，并且操纵视频片段ID的排列。 因此，即使执行编辑，也不会在参照元数据信息时产生不一致之处，因此等同于与移动图像编辑同步更新的元数据。 因此，可以自动进行运动图像的虚拟编辑，然后更新元数据，并且还减轻了重新编辑编辑器的元数据的负担。

公开(公告)号：US20070122037A1

公开(公告)日：2007-05-31

申请号：US11598026

申请日：2006-11-13

Applicant: Hirotaka Shiiyama

Inventor： Hirotaka Shiiyama

IPC: G06K9/46

CPC classification number: G06K9/2063 ,  G06K2209/01

Abstract: Of the feature amounts of respective regions on an image, a region having a feature amount which is similar to that of a region of interest on a image is specified (S1307). Of the OCR results of the respective regions on the image, a region having an OCR result which matches that of the region of interest on the image is specified (S1308). Regions corresponding to respective regions on the image of the respective regions are specified based on the layout order of the specified regions (S1311). Of the regions obtained by combining neighboring regions on the image, a region corresponding to an inclusion region that includes each specified region is specified (S1314).

Abstract translation: 在图像上的各个区域的特征量中，指定具有与图像上的感兴趣区域的特征量相似的特征量的区域（S1307）。 在图像上的相应区域的OCR结果中，指定具有与图像上的感兴趣区域的OCR结果匹配的OCR结果的区域（S1308）。 基于指定区域的布局顺序来指定与各个区域的图像上的各个区域对应的区域（S1311）。 在通过组合图像上的相邻区域获得的区域中，指定与包括每个指定区域的包含区域对应的区域（S1313）。

公开(公告)号：US20060110073A1

公开(公告)日：2006-05-25

申请号：US11280234

申请日：2005-11-17

Applicant: Masahiro Matsushita ,  Hirotaka Shiiyama

Inventor： Masahiro Matsushita ,  Hirotaka Shiiyama

IPC: G06K9/54 ,  G06F17/30

CPC classification number: G06K9/6206 ,  G06F17/30247

Abstract: This invention has as its object to allow high-precision and high-speed retrieval in consideration of position information of image feature amounts upon retrieving similar images based on image feature amounts, even when the position information includes some differences. To achieve such object, an image processing apparatus according to this invention has the following arrangement. That is, an image processing apparatus for calculating a similarity between different image data, includes a first generation unit configured to generate feature amount matrices on the basis of feature amounts of the image data acquired by dividing the different image data into a plurality of blocks, a calculation unit configured to calculate a distance between feature sequences which form the generated feature amount matrices by DP matching, and a second generation unit configured to generate a line penalty matrix by two-dimensionally arranging the calculated distances between the feature sequences, and calculates a similarity between the different image data by DP matching using the line penalty matrix.