公开(公告)号：US07319811B2

公开(公告)日：2008-01-15

申请号：US10186641

申请日：2002-07-02

申请人： Hiroshi Tojo ,  Satoshi Nakayama

发明人： Hiroshi Tojo ,  Satoshi Nakayama

IPC分类号： H04N5/76 ,  H04N7/00 ,  H04N5/00

CPC分类号： H04N5/2628 ,  H04N5/772 ,  H04N5/781 ,  H04N5/85 ,  H04N5/907 ,  H04N9/8042

摘要： A moving image processing apparatus can perform a zoom process for each frame image of moving image data in an digital zoom section. An image quality determining section determines an image quality of a frame image obtained through the zoom process in reproduction, when this zoom process is performed, and passes quality information representing its determined result to an MPEG CODEC. The MPEG CODEC encodes the moving image data processed in the digital zoom section and a noise reduction section, and stores the image data, and the quality information associated with each frame in a storage medium. In this manner, when the reproduction object data is processed to have some effect on the quality in reproduction, the data can be provided with the information regarding the quality in reproduction.

摘要翻译： 运动图像处理装置可以对数字变焦部分中的运动图像数据的每个帧图像执行缩放处理。 当进行该缩放处理时，图像质量确定部分确定通过再现中的缩放处理获得的帧图像的图像质量，并将表示其确定结果的质量信息传递到MPEG编解码器。 MPEG CODEC编码在数字变焦部分中处理的运动图像数据和噪声降低部分，并将图像数据和与每个帧相关联的质量信息存储在存储介质中。 以这种方式，当再现对象数据被处理以对再现质量有一些影响时，可以向数据提供关于再现质量的信息。

公开(公告)号：US08866900B2

公开(公告)日：2014-10-21

申请号：US12613052

申请日：2009-11-05

申请人： Hidetomo Sohma ,  Hiroshi Tojo ,  Satoshi Yashiro

发明人： Hidetomo Sohma ,  Hiroshi Tojo ,  Satoshi Yashiro

IPC分类号： H04N9/47 ,  H04N7/18 ,  H04N5/14 ,  H04N9/64 ,  G06T7/20 ,  G06K9/00

CPC分类号： H04N5/147 ,  G06K9/00228 ,  G06T7/248 ,  G06T2207/10016 ,  G06T2207/30201

摘要： An information processing apparatus for extracting a more appropriate representative frame image from moving image data that includes a plurality of frames of image data arranged in a time series includes: an input unit configured to input moving image data; a detecting unit configured to detect a frame image, which includes an image similar to a prescribed image pattern; a tracking unit configured to detect a frame image, which includes an image similar to the image included in the detected frame image; a storage unit configured to store the successive frame images in association with time information; a splitting unit configured to split the moving image data into a plurality of time intervals with starting time and end time of each of one or more image sequences; and an extracting unit configured to extract a representative frame image.

摘要翻译： 一种用于从包括以时间序列排列的多个图像数据的运动图像数据提取更适当的代表性帧图像的信息处理装置，包括：输入单元，被配置为输入运动图像数据; 检测单元，被配置为检测包括与规定图像图案相似的图像的帧图像; 跟踪单元，被配置为检测帧图像，所述帧图像包括类似于所检测帧图像中包含的图像的图像; 存储单元，被配置为与时间信息相关联地存储连续的帧图像; 分割单元，被配置为将运动图像数据分割成多个时间间隔，其中一个或多个图像序列中的每一个的开始时间和结束时间; 以及提取单元，被配置为提取代表性帧图像。

公开(公告)号：US08718128B2

公开(公告)日：2014-05-06

申请号：US10829437

申请日：2004-04-22

申请人： Hiroshi Tojo

发明人： Hiroshi Tojo

IPC分类号： H04N7/12

CPC分类号： H04N5/772 ,  G11B27/034 ,  G11B27/105 ,  G11B27/329 ,  G11B27/34 ,  G11B2220/20 ,  H04N5/781 ,  H04N5/85 ,  H04N5/907 ,  H04N9/8042 ,  H04N9/8205

摘要： A moving image is divided on the basis of a plurality of items of additional data which indicate states upon sensing the moving image. The additional data is added to the moving image and is able to be read out for each item from the moving image. An item group formed of one or a plurality of items selected from the plurality of items is defined, and division information corresponding to the item group is generated on the basis of the additional data of the items which belong to the item group. In a case that a plurality of division information are generated in correspondence with a plurality of item groups, the plurality of division information generated for each item group are hierarchized, and division positions are added. The division information is held in correspondence with the moving image data.

摘要翻译： 基于感测运动图像的指示状态的多个附加数据项，分割运动图像。 附加数据被添加到运动图像，并且能够从运动图像中读出每个项目。 定义从多个项目中选择的一个或多个项目形成的项目组，并且根据属于项目组的项目的附加数据生成对应于项目组的划分信息。 在与多个项目组相对应地生成多个分割信息的情况下，对每个项目组生成的多个分割信息进行分层，并且分配位置被相加。 与运动图像数据对应地保持分割信息。

公开(公告)号：US08525935B2

公开(公告)日：2013-09-03

申请号：US12121909

申请日：2008-05-16

申请人： Hiroshi Tojo

发明人： Hiroshi Tojo

IPC分类号： H04N5/14 ,  G06K9/34 ,  G06K9/36 ,  G06K9/64

CPC分类号： G06K9/00711 ,  G06T7/254 ,  G06T2207/10016 ,  G11B27/28 ,  G11B2220/90 ,  H04N5/147

摘要： A frame extraction unit detects a luminance change point frame in which the brightness change amount between frames is equal to or higher than a threshold value from a moving image formed by a plurality of frames. A flash check unit checks the presence/absence of a flash portion in the moving image on the basis of the detected luminance change point frame.

公开(公告)号：US08351660B2

公开(公告)日：2013-01-08

申请号：US12395067

申请日：2009-02-27

申请人： Muling Guo ,  Satoshi Yashiro ,  Hiroshi Tojo

发明人： Muling Guo ,  Satoshi Yashiro ,  Hiroshi Tojo

IPC分类号： G06K9/00

CPC分类号： G06K9/00268 ,  G06K9/00234 ,  G06K9/00369 ,  G06K9/00778 ,  Y10T117/1036 ,  Y10T117/1064

摘要： A face area is detected from an image captured by an image pickup device, pixel values of the image are adjusted based on information concerning the detected face area, a person area is detected from the adjusted image, and the detected face area is integrated with the detected person area. With this configuration, it is possible to accurately detect an object even in a case, for example, where the brightness is varied.

公开(公告)号：US07746507B2

公开(公告)日：2010-06-29

申请号：US11460548

申请日：2006-07-27

申请人： Masahiro Matsushita ,  Hiroshi Tojo

发明人： Masahiro Matsushita ,  Hiroshi Tojo

IPC分类号： H04N1/40

CPC分类号： G06F17/30011 ,  G06F17/30247 ,  G06K9/00463 ,  G06K9/00483

摘要： Even if a margin area, which did not exist in an original image, is present around a document area in a document acquired by printing the original image, an accurate layout comparison between the scanned image of the printed document and the original image can be performed as follows. An original image serving as a comparison target image is input, and block information about a block included in the original image is extracted. It is determined whether the size of the original image is a predetermined size. When the size is not a predetermined size, block information about the block included in the original image mapped to a predetermined size is created and registered. When a comparison source image is input, block information about a block included in the comparison source image is extracted. Subsequently, two pieces of the block information of the comparison source and target images are compared.

摘要翻译： 即使在原始图像中不存在的边缘区域存在于通过打印原始图像获取的文档中的文档区域周围，可以执行打印文档的扫描图像与原始图像之间的精确布局比较 如下。 输入用作比较对象图像的原始图像，并且提取关于包含在原始图像中的块的块信息。 确定原始图像的尺寸是否为预定尺寸。 当尺寸不是预定尺寸时，创建并注册关于映射到预定尺寸的原始图像中包含的块的块信息。 当输入比较源图像时，提取关于包括在比较源图像中的块的块信息。 随后，比较两个比较源和目标图像的块信息。

公开(公告)号：US07623259B2

公开(公告)日：2009-11-24

申请号：US11223986

申请日：2005-09-13

申请人： Hiroshi Tojo

发明人： Hiroshi Tojo

IPC分类号： G06F3/12

CPC分类号： G06K9/036 ,  G06K9/00463

摘要： From an already registered image data group, image data similar to image data input as a query are retrieved (S3190). When image quality of one of the retrieved image data is lower than that of the input image data, the input image data is registered in place of the one image data (S3163).

摘要翻译： 从已经登记的图像数据组中，检索与作为查询输入的图像数据相似的图像数据（S3190）。 当检索到的图像数据之一的图像质量低于输入图像数据的图像质量时，输入图像数据被替换为一个图像数据（S3163）。

公开(公告)号：US20050027745A1

公开(公告)日：2005-02-03

申请号：US10930852

申请日：2004-09-01

申请人： Hidetomo Sohma ,  Hiroshi Tojo ,  Masanori Itoh ,  Masafumi Shimotashiro ,  Tadashi Nakamura

发明人： Hidetomo Sohma ,  Hiroshi Tojo ,  Masanori Itoh ,  Masafumi Shimotashiro ,  Tadashi Nakamura

IPC分类号： H04N5/76 ,  G06F17/30 ,  G11B27/00 ,  G11B27/034 ,  G11B27/10 ,  G11B27/32 ,  H04N5/91 ,  G06F17/00

CPC分类号： G06F17/30817 ,  G11B27/034 ,  G11B27/105 ,  G11B27/329 ,  G11B2220/90

摘要： For multiple moving-image recorded on a storage medium, one piece of meta-data or each of multiple pieces of meta-data recorded for a part or all of the moving-image is managed by meta-data indices. A meta-data index keeps invalidity information indicating whether a piece of meta-data is going to be invalid and validity information indicating validity of the current piece of meta-data in the same form, when operations such as editing and processing are performed on a part or all of a moving-image that is an object of a piece of meta-data. When cutting-out occurs on a section of a moving-image that is an object of a piece of meta-data and the piece of meta-data cannot be recalculated, the invalidity information is copied to the validity information. In this manner, a meta-data added to the moving-image can be adapted and be used after the moving-image is edited.

摘要翻译： 对于记录在存储介质上的多个运动图像，通过元数据索引来管理为一部分或全部运动图像记录的一条元数据或多条元数据中的每一条。 元数据索引保持指示一条元数据是否无效的无效信息以及指示当前操作如同编辑和处理的同一形式的当前元数据的有效性的有效性信息 作为元数据的对象的运动图像的部分或全部。 当作为元数据的对象的运动图像的一部分发生切割时，不能重新计算该元数据片段时，将无效信息复制到有效信息。 以这种方式，添加到运动图像的元数据可以在运动图像被编辑之后被适配和使用。

公开(公告)号：US08818096B2

公开(公告)日：2014-08-26

申请号：US13212619

申请日：2011-08-18

申请人： Hiroshi Tojo

发明人： Hiroshi Tojo

IPC分类号： G06K9/34

CPC分类号： G06T7/254 ,  G06T2207/20081

摘要： An image processing apparatus includes a calculation unit configured to calculate a difference between a feature quantity of input video data and a feature quantity of a model representing a background, a determination unit configured to determine whether a partial area in the input video data is a foreground or a background based on the difference, a detection unit configured to detect a subject area from an area determined to be a foreground, a first update unit configured to update appearance information that represents an appearance state of a background relating to the subject area, and a second update unit configured to update the model based on the appearance information.

摘要翻译： 一种图像处理装置包括：计算单元，被配置为计算输入视频数据的特征量与表示背景的模型的特征量之间的差;确定单元，被配置为确定输入视频数据中的部分区域是否为前景 或基于该差异的背景，检测单元，被配置为从被确定为前景的区域检测主题区域;第一更新单元，被配置为更新表示与所述主题区域相关的背景的外观状态的外观信息;以及 第二更新单元，被配置为基于所述外观信息更新所述模型。

公开(公告)号：US08797381B2

公开(公告)日：2014-08-05

申请号：US12684012

申请日：2010-01-07

申请人： Hiroshi Tojo

发明人： Hiroshi Tojo

IPC分类号： H04N5/232 ,  G06K9/00

CPC分类号： H04N7/142 ,  G06T7/77 ,  G06T2207/10016 ,  G06T2207/30201 ,  H04N5/232 ,  H04N5/23229 ,  H04N5/23296

摘要： An image processing apparatus includes a photographing unit configured to generate a plurality of images by photographing a plurality of times a range which can be photographed, an object detection unit configured to detect a specified object from each of the plurality of images generated by the photographing unit, a position determination unit configured to determine an existing position of the specified object based on a detection result of the specified object in the plurality of images, and a range determination unit configured to determine a photographing range to be photographed within the range which can be photographed based on the existing position of the specified object determined by the position determination unit.

摘要翻译： 一种图像处理装置，包括拍摄单元，被配置为通过多次拍摄可拍摄的范围来生成多个图像;物体检测单元，被配置为从拍摄单元生成的多个图像中的每一个中检测指定的对象 ，位置确定单元，被配置为基于所述多个图像中的指定对象的检测结果来确定所述指定对象的现有位置;以及范围确定单元，被配置为在所述多个图像的范围内确定要拍摄的拍摄范围 基于由位置确定单元确定的指定对象的现有位置拍摄。