公开(公告)号：US20060285748A1

公开(公告)日：2006-12-21

申请号：US11319359

申请日：2005-12-29

申请人： Masakazu Tateno ,  Kei Tanaka ,  Kotaro Nakamura ,  Takashi Nagao ,  Masayoshi Sakakibara ,  Xinyu Peng ,  Teruka Saito ,  Toshiya Koyama

发明人： Masakazu Tateno ,  Kei Tanaka ,  Kotaro Nakamura ,  Takashi Nagao ,  Masayoshi Sakakibara ,  Xinyu Peng ,  Teruka Saito ,  Toshiya Koyama

IPC分类号： G06K9/00 ,  G06F17/28

CPC分类号： G06F17/289 ,  G06F17/275 ,  G06K9/00456

摘要： A document processing device comprises: an image capturing unit that captures an image and acquires image data; a region separating section that extracts from the image data, image data of a printed region and image data of a hand-drawn region; a printed text data acquiring section that acquires printed text data in the printed region; a hand-drawn text data acquiring section that acquires hand-drawn text data in the hand-drawn region; a printed language specifying section that specifies language of the printed text data; a hand-drawn language specifying section that specifies language of the hand-drawn text data; a translation processing section that generates translated text data by translating the printed text data to the language that has been specified by the hand-drawn language specifying section.

摘要翻译： 文件处理装置包括：图像捕获单元，其捕获图像并获取图像数据; 从图像数据提取的区域分离部分，打印区域的图像数据和手绘区域的图像数据; 印刷文本数据获取部分，其获取所述打印区域中的打印文本数据; 手绘文本数据获取部，其获取手绘区域中的手绘文字数据; 印刷语言指定部分，其指定打印文本数据的语言; 指定手绘文本数据的语言的手绘语言指定部分; 翻译处理部分，通过将打印的文本数据翻译成由手绘语言指定部分指定的语言来生成翻译的文本数据。

公开(公告)号：US07844893B2

公开(公告)日：2010-11-30

申请号：US11210898

申请日：2005-08-25

申请人： Teruka Saito ,  Toshiya Koyama ,  Masakazu Tateno ,  Takashi Nagao ,  Masayoshi Sakakibara ,  Kei Tanaka ,  Kotaro Nakamura ,  Xinyu Peng

发明人： Teruka Saito ,  Toshiya Koyama ,  Masakazu Tateno ,  Takashi Nagao ,  Masayoshi Sakakibara ,  Kei Tanaka ,  Kotaro Nakamura ,  Xinyu Peng

IPC分类号： G06F17/00

CPC分类号： G06F17/241

摘要： A document editing device has a editing unit and a supplementary information editing unit. The editing unit edits a manuscript element of a document. The supplementary information editing unit edits the supplementary information of the document based on a result of editing the manuscript element by the editing unit. The document is a electronic document read by a reading device.

摘要翻译： 文件编辑装置具有编辑单元和辅助信息编辑单元。 编辑单元编辑文档的原稿元素。 补充信息编辑单元基于由编辑单元编辑原稿元素的结果来编辑文档的补充信息。 该文件是由读取装置读取的电子文档。

公开(公告)号：US07729540B2

公开(公告)日：2010-06-01

申请号：US11224050

申请日：2005-09-13

申请人： Toshiya Koyama ,  Teruka Saito ,  Masakazu Tateno ,  Kei Tanaka ,  Takashi Nagao ,  Masayoshi Sakakibara ,  Xinyu Peng ,  Kotaro Nakamura

发明人： Toshiya Koyama ,  Teruka Saito ,  Masakazu Tateno ,  Kei Tanaka ,  Takashi Nagao ,  Masayoshi Sakakibara ,  Xinyu Peng ,  Kotaro Nakamura

IPC分类号： G06K9/34 ,  G06K9/32 ,  G06K15/00 ,  H04N1/40 ,  G06T5/00 ,  G06F17/28

CPC分类号： G06K9/00469 ,  G06F17/289

摘要： A translation device has a translation processing unit that outputs character-area-character data by performing a translation process on the character-area-character data of an input image representing a figure-containing document, and outputting figure-area-character data by performing a translation process on the figure-area-character data of an input image representing a figure-containing document, a figure identification information searching unit that searches figure identification information used to identify a figure contained in a character area of the figure-containing-translation data, a linked page number searching unit that searches a page number in a character area of the figure-containing-translation data, a page number extracting unit that extracts a page number of a page included in figure area of figure identification information, and a page number rewriting unit that rewrites the searched page number linked to the figure identification information to the extracted page number of a page.

摘要翻译： 翻译装置具有翻译处理单元，其通过对表示包含文字的文档的输入图像的字符区域字符数据进行翻译处理来输出字符区域字符数据，并且通过执行图形区域字符数据来输出图形区域字符数据 表示包含图形的文档的输入图像的图形区域字符数据的翻译处理，图形识别信息搜索单元，其搜索用于识别包含在包含图像的文本的字符区域中的图形的图形识别信息 数据，链接页码搜索单元，搜索包含图形的翻译数据的字符区域中的页码;页码提取单元，提取包含在图形识别信息的图形区域中的页面的页码，以及 页编号重写单元，其将与图标识别信息相关联的搜索到的页码重写为提取的标签 e页数。

公开(公告)号：US07558422B2

公开(公告)日：2009-07-07

申请号：US10775242

申请日：2004-02-11

申请人： Toshiya Koyama ,  Teruka Saito

发明人： Toshiya Koyama ,  Teruka Saito

IPC分类号： G06K9/00 ,  G09G5/02

CPC分类号： H04N1/6075 ,  H04N1/40012

摘要： A document processing apparatus has a control section. The control section determines that at least some of a plurality of colors contained in input document data are a determined color group, determines at least one set of confusion colors of the colors contained in the determined color group based on confusion color information defined in association with color blindness of a human being in a predetermined color component space, and performs predetermined process for portions of the colors contained in the determined confusion color set, in the input document data.

摘要翻译： 文件处理装置具有控制部。 控制部分确定输入文档数据中包含的多种颜色中的至少一些是确定的颜色组，基于与所确定的颜色组相关联地定义的混淆颜色信息来确定包含在所确定的颜色组中的颜色的至少一组混淆颜色 在预定颜色分量空间中的人的色盲，并且对输入的文档数据中对于所确定的混合色彩集合中包含的部分颜色执行预定处理。

公开(公告)号：US07469063B2

公开(公告)日：2008-12-23

申请号：US11079178

申请日：2005-03-15

申请人： Toshiya Koyama ,  Teruka Saito ,  Masakazu Tateno ,  Kei Tanaka ,  Masayoshi Sakakibara ,  Kotaro Nakamura

发明人： Toshiya Koyama ,  Teruka Saito ,  Masakazu Tateno ,  Kei Tanaka ,  Masayoshi Sakakibara ,  Kotaro Nakamura

IPC分类号： G06K9/00 ,  G06K7/10 ,  G06K9/20 ,  H04N1/04

CPC分类号： G06K9/6835 ,  G06K9/00456

摘要： An apparatus for recognizing characters includes a text structure analyzing unit that analyzes an input image of text composed of mixed typed and handwritten characters and separates the input text image into predefined text imaging regions, a character clipping unit that clips characters one by one in each of the text imaging regions separated by the text structure analyzing unit, a feature vectors calculating unit that calculates feature vectors of the clipped characters for each of the text imaging regions, a feature vectors aggregating unit that aggregates the calculated feature vectors over a predefined range of the input text image, and a typed and handwritten character separation unit that separates characters involved in the input text image into the typed characters and the handwritten characters, based on a result of the aggregation by the feature vectors aggregating unit.

摘要翻译： 用于识别字符的装置包括：文本结构分析单元，分析由混合类型和手写字符组成的文本的输入图像，并将输入的文本图像分离成预定义的文本成像区域;字符剪辑单元， 由文本结构分析单元分离的文本成像区域，计算每个文本成像区域的剪切字符的特征向量的特征向量计算单元，在所述文本结构分析单元的预定范围内聚合计算出的特征向量的特征向量聚合单元， 输入文本图像，以及键入和手写字符分离单元，其基于特征向量聚合单元的聚合结果将输入文本图像中涉及的字符分离成类型字符和手写字符。

公开(公告)号：US20060062459A1

公开(公告)日：2006-03-23

申请号：US11218492

申请日：2005-09-06

申请人： Teruka Saito ,  Toshiya Koyama ,  Masayoshi Sakakibara ,  Masakazu Tateno ,  Kei Tanaka ,  Kotaro Nakamura

发明人： Teruka Saito ,  Toshiya Koyama ,  Masayoshi Sakakibara ,  Masakazu Tateno ,  Kei Tanaka ,  Kotaro Nakamura

IPC分类号： G06K9/00

CPC分类号： G06K9/6835 ,  G06K9/00456

摘要： A character recognition apparatus includes: a separation processing unit that separates, into printed character portions and handwritten character portions, data of a document in which printed characters and handwritten characters are mixed; a printed character portion recognition processing unit that character-recognizes the printed character portions; and a handwritten character portion recognition processing unit that utilizes the character recognition result of the printed character portions to character-recognize the handwritten character portions.

摘要翻译： 一种字符识别装置，包括：分离处理单元，将打印字符和手写字符混合在一起的文档的数据分离成打印字符部分和手写字符部分; 打印字符部分识别处理单元，其字符识别打印的字符部分; 以及手写字符部分识别处理单元，其使用打印的字符部分的字符识别结果来字符识别手写字符部分。

公开(公告)号：US20060045340A1

公开(公告)日：2006-03-02

申请号：US11080489

申请日：2005-03-16

申请人： Masayoshi Sakakibara ,  Kotaro Nakamura ,  Masakazu Tateno ,  Kei Tanaka ,  Teruka Saito ,  Toshiya Koyama

发明人： Masayoshi Sakakibara ,  Kotaro Nakamura ,  Masakazu Tateno ,  Kei Tanaka ,  Teruka Saito ,  Toshiya Koyama

IPC分类号： G06K9/18

CPC分类号： G06K9/2054 ,  G06K2209/01

摘要： The present invention provides a character recognition apparatus including: plural dictionary databases that contain terms or characters classified into respective fields; a determination unit that determines which field the contents of a document shown by document image data belong to; a selection unit that selects a dictionary database pertaining to the field determined by the determination unit from among the plural dictionary databases; a recognition unit that recognizes a term or a character written in the document shown by the document image data by using the terms or characters stored in the selected dictionary database as candidates; and an output unit that outputs the result of recognition by the recognition unit.

摘要翻译： 本发明提供一种字符识别装置，包括：多个字典数据库，其包含分类为各个字段的项或字符; 确定单元，其确定由文档图像数据所显示的文档的内容属于哪个字段; 选择单元，从所述多个词典数据库中选择与由所述确定单元确定的字段相关的词典数据库; 识别单元，通过使用存储在所选择的字典数据库中的术语或字符来识别由文档图像数据所示的文档中写入的术语或字符作为候选; 以及输出单元，其输出识别单元的识别结果。

公开(公告)号：US07969631B2

公开(公告)日：2011-06-28

申请号：US11606907

申请日：2006-12-01

申请人： Toshiya Koyama

发明人： Toshiya Koyama

IPC分类号： H04N1/46 ,  G06K9/34

CPC分类号： G06K9/222 ,  G06K9/00456

摘要： An image processing apparatus includes an area splitting section that splits whole image areas of a first page before edition and a second page which has been edited into plural regions; an alignment section that performs relative alignments between each of the corresponding split regions of the first page image and the second page image, produced by the area splitting section; and an extraction section that extracts edit information from the second page image by comparing the first page image with the second mage image which have been aligned by the alignment section.

摘要翻译： 一种图像处理装置包括：区域划分部，其在编辑前分割第一页的整个图像区域;以及第二页面，其被编辑为多个区域; 对准部，其对由所述区域分割部生成的所述第一页图像的对应的分割区域和所述第二页面图像进行相对对准; 以及提取部，其通过将所述第一页图像与所述对准部对准的所述第二法师图像进行比较，从所述第二页图像提取编辑信息。

公开(公告)号：US07865130B2

公开(公告)日：2011-01-04

申请号：US11225131

申请日：2005-09-14

申请人： Toshiya Koyama ,  Nobuhiro Nozaki ,  Ichiro Shimomura

发明人： Toshiya Koyama ,  Nobuhiro Nozaki ,  Ichiro Shimomura

IPC分类号： G09B3/00

CPC分类号： G09B7/02

摘要： A material processing method has a process of reading image data of a material. The material has answer fields and information items on points distributed to the answer fields. The method also has extracting the distributed point information items based on the image data, associating the distributed point information items with answer fields to recognize the points distributed to each answer field, storing a result recognized the points distributed to each answer field as answer/distributed point correspondence information, recognizing correct/incorrect answer determining contents from the image data, and performing point totaling on the correct/incorrect answer determining contents based on the answer/distributed point correspondence information.

摘要翻译： 材料处理方法具有读取材料的图像数据的处理。 材料在分发到答案字段的点上有答案字段和信息项。 该方法还基于图像数据提取分布点信息项，将分布式点信息项与应答字段相关联，以识别分配给每个应答字段的点，将分配给每个应答字段的点的结果存储为应答/分布 点对应信息，从图像数据识别正确/不正确的答案确定内容，以及基于答案/分布点对应信息对正确/不正确的答案确定内容执行点总计。

公开(公告)号：US06333117B1

公开(公告)日：2001-12-25

申请号：US09499388

申请日：2000-02-07

申请人： Hiroyuki Sumi ,  Toshiya Koyama

发明人： Hiroyuki Sumi ,  Toshiya Koyama

IPC分类号： B32B904

CPC分类号： B32B7/06 ,  A61K9/703 ,  B32B25/20 ,  B32B27/08 ,  B32B27/283 ,  B32B27/36 ,  B32B2307/518 ,  B32B2367/00 ,  B32B2439/80 ,  C08J7/04 ,  C08J7/047 ,  C08J2367/02 ,  C08J2483/00 ,  C09J7/403 ,  C09J2467/006 ,  C09J2483/005 ,  Y10S428/91 ,  Y10T428/14 ,  Y10T428/31663 ,  Y10T428/31667

摘要： A releasing film (C) comprising a polyester film (A) and a cured silicone resin layer (B) formed on at least one side of the polyester film (A), characterized in that (1) the film (A) is a biaxially oriented film formed of polyethylene-2,6-naphthalenedicarboxylate and has a surface center line average roughness (Ra) of 50 nm or less and (2) the releasing film (C) has a dimensional change of 0.2% or less under a stress of 150 gf/mm2 at 120° C.; and a releasing film (C) comprising a primer layer (D) having a SiO bond, between said film (A) and said cured silicone resin layer (B). The releasing film of the present invention is excellent in heat resistance, surface properties and gas barrier properties, and has small dimensional change rate.

摘要翻译： 1.一种在聚酯膜（A）的至少一面上形成有聚酯膜（A）和固化有机硅树脂层（B）的剥离膜（C），其特征在于，（1）膜（A）为双轴 由聚乙烯-2,6-萘二甲酸酯形成的取向膜，其中心线平均粗糙度（Ra）为50nm以下，（2）剥离膜（C）的应变为0.2％以下，尺寸变化为 在120°C时为150 gf / mm2。 和在所述膜（A）和所述固化的有机硅树脂层（B）之间的包含具有SiO键的底漆层（D）的剥离膜（C）。 本发明的剥离膜的耐热性，表面性质和阻气性优异，尺寸变化率小。