专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

91. 发明授权

EP0431843B1 Character recognition apparatus 失效
标题翻译：字符识别设备
公开(公告)号：EP0431843B1
公开(公告)日：1997-09-10
申请号：EP90313016.9
申请日：1990-11-30
申请人： SONY CORPORATION
发明人： Aguro, Masayuki, c/o Patents Division , Tanaka, Hidekazu, c/o Patents Division , Yoshida, Kimiyoshi, c/o Patents Division , Sakano, Akio, c/o Patents Division
IPC分类号： G06K9/22 , G06K9/68
CPC分类号： G06K9/6255 , G06K9/6807

92. 发明公开

EP0715274A3 Method and apparatus for detecting whether an electronic image has been faxed 失效
标题翻译：是否一个电子图像传真方法和装置，以找出
公开(公告)号：EP0715274A3
公开(公告)日：1997-02-05
申请号：EP95308693.1
申请日：1995-12-01
申请人： XEROX CORPORATION
发明人： Saund, Eric
IPC分类号： G06K9/00
CPC分类号： G06K9/6807
摘要： A method of recognizing the effects of coarse pixel quantization on text represented via raster signals that enables automatic selection between the fax and normal modes of a optical character recognition unit (33), in order to enhance the reading performance of the optical character recognition unit for lower resolution images produced by facsimile machines. A processor (40) executes instructions stored in a memory (41) to trace the contours of connected components (51,90) included within a sample image (32) in a document (31) and to count the number of runs one, two, and three pixels in length along the contour. If the sample image includes few runs of two pixels in length along the contours of its connected components as compared to the number of runs of one and three pixels in length, then the sample image has undergone coarse pixel quantization and the processor selects the fax mode of the optical character recognition unit.

93. 发明公开

EP0715274A2 Method and apparatus for detecting whether an electronic image has been faxed 失效
标题翻译： Verfahren undGerät，um herauszufinden，obein elektronisches Bild gefaxt wurde
公开(公告)号：EP0715274A2
公开(公告)日：1996-06-05
申请号：EP95308693.1
申请日：1995-12-01
申请人： XEROX CORPORATION
发明人： Saund, Eric
IPC分类号： G06K9/00
CPC分类号： G06K9/6807
摘要： A method of recognizing the effects of coarse pixel quantization on text represented via raster signals that enables automatic selection between the fax and normal modes of a optical character recognition unit (33), in order to enhance the reading performance of the optical character recognition unit for lower resolution images produced by facsimile machines. A processor (40) executes instructions stored in a memory (41) to trace the contours of connected components (51,90) included within a sample image (32) in a document (31) and to count the number of runs one, two, and three pixels in length along the contour. If the sample image includes few runs of two pixels in length along the contours of its connected components as compared to the number of runs of one and three pixels in length, then the sample image has undergone coarse pixel quantization and the processor selects the fax mode of the optical character recognition unit.
摘要翻译：识别粗略像素量化对通过光栅信号表示的文本的影响的方法，其能够在光学字符识别单元（33）的传真和正常模式之间进行自动选择，以便增强光学字符识别单元的读取性能传真机产生的较低分辨率图像。处理器（40）执行存储在存储器（41）中的指令，以跟踪包含在文档（31）中的样本图像（32）内的连接的组件（51,90）的轮廓，并对运行次数，沿着轮廓长度为三个像素。如果样本图像与其连接的分量的轮廓相比长度为两个像素的长度相比，长度为一个和三个像素的运行次数，则样本图像经历了粗略的像素量化，并且处理器选择传真模式的光学字符识别单元。

94. 发明公开

EP0651346A3 Forms recognition management system and method 失效
标题翻译：方法和系统管理的形式认可。
公开(公告)号：EP0651346A3
公开(公告)日：1995-07-26
申请号：EP94115179.7
申请日：1994-09-27
申请人： International Business Machines Corporation
发明人： Burger, Mark E. , Sun, Hsiao
IPC分类号： G06K9/68
CPC分类号： G06K9/2054 , G06K9/6807 , G06K2209/01
摘要： Document form templates are grouped into groups of related form templates. The number of times a particular template is used by the system is counted for each group during a forms processing interval. Then when processing submitted forms, the method scans in a plurality of them in an aggregated submission. Forms recognition processing starts for a first form. The method begins searching for a form template to match the first form, starting with the most frequent group. If recognition of the first form is successful with the most frequent primary form template, then the method searches the group for the remaining submitted forms. If recognition of the first form is not successful with the most frequent group, then the method tries to match the first form with a template in the second most frequently processed primary group. In this manner, forms recognition of preprinted forms is managed, with the order of searching the template archive changed in response to the frequency with which particular form types are processed.

95. 发明公开

EP0651346A2 Forms recognition management system and method 失效
标题翻译：表格识别管理系统和方法
公开(公告)号：EP0651346A2
公开(公告)日：1995-05-03
申请号：EP94115179.7
申请日：1994-09-27
申请人： International Business Machines Corporation
发明人： Burger, Mark E. , Sun, Hsiao
IPC分类号： G06K9/68
CPC分类号： G06K9/2054 , G06K9/6807 , G06K2209/01
摘要： Document form templates are grouped into groups of related form templates. The number of times a particular template is used by the system is counted for each group during a forms processing interval. Then when processing submitted forms, the method scans in a plurality of them in an aggregated submission. Forms recognition processing starts for a first form. The method begins searching for a form template to match the first form, starting with the most frequent group. If recognition of the first form is successful with the most frequent primary form template, then the method searches the group for the remaining submitted forms. If recognition of the first form is not successful with the most frequent group, then the method tries to match the first form with a template in the second most frequently processed primary group. In this manner, forms recognition of preprinted forms is managed, with the order of searching the template archive changed in response to the frequency with which particular form types are processed.
摘要翻译：文档表单模板被分组到相关表单模板的组中。在表单处理间隔期间，为每个组计算系统使用特定模板的次数。然后，在处理提交的表单时，该方法在汇总的提交中扫描多个表单。表单识别处理以第一种形式开始。该方法开始搜索表单模板以匹配第一个表单，从最频繁的组开始。如果第一种形式的识别对于最常见的主要表单模板是成功的，那么该方法搜索组中剩余的提交表单。如果第一种形式的识别对于最频繁的组不成功，那么该方法试图将第一种形式与第二种最频繁处理的主要组中的模板进行匹配。以这种方式，管理预打印表格的表格识别，其中搜索响应于处理特定表格类型的频率而改变的模板存档的顺序。

96. 发明公开

EP0585944A3 Information processing method and apparatus 失效
标题翻译： Informationsverarbeitungsverfahren und -vorrichtung。
公开(公告)号：EP0585944A3
公开(公告)日：1994-12-07
申请号：EP93114158.4
申请日：1993-09-03
申请人： CANON KABUSHIKI KAISHA
发明人： Arai, Tsunekazu, c/o Canon Kabushiki Kaisha , Sakaguchi, Katsuhiko, c/o Canon Kabushiki Kaisha , Mori, Shigeki, c/o Canon Kabushiki Kaisha , Matsubayashi, Kazuhiro, c/o Canon Kabushiki Kaisha , Harada, Takashi, c/o Canon Kabushiki Kaisha , Takasu, Eiji, c/o Canon Kabushiki Kaisha , Yoshii, Hiroto, c/o Canon Kabushiki Kaisha
IPC分类号： G06K9/64 , G06K9/03
CPC分类号： G06K9/6807 , G06K9/00429 , G06K9/6255
摘要： An information processing method including memorizing pattern information, memorizing use information of said pattern information memorized, and displaying said pattern information memorized and said use information of said pattern information.
摘要翻译：一种信息处理方法，包括存储图案信息，存储所存储的所述图案信息的使用信息，以及显示存储的所述图案信息和所述图案信息的所述使用信息。

97. 发明公开

EP0621552A2 Method and apparatus for automatic character script determination 失效
标题翻译： Verfahren undGerätzur automatischen Schriftermittlung。
公开(公告)号：EP0621552A2
公开(公告)日：1994-10-26
申请号：EP94302739.1
申请日：1994-04-18
申请人： XEROX CORPORATION
发明人： Spitz, A. Lawrence , Hull, David A.
IPC分类号： G06F15/20 , G06K9/72
CPC分类号： G06K9/6807
摘要： An automatic script-determining apparatus automatically determines the gross script-type of the text image of a document. A connected component generating means (28) generates connected components from the pixels comprising the text image. A bounding box generating means (30) generates a bounding box surrounding each connected component. A centroid determining means (32) determines a centroid for each bounding box. A script feature determining means (34) determines the locations, relative to the centroid, of one or more predetermined types of features, for each bounding box. A script determining means (36) determines a distribution of the located script features for the entire text image, and compares the determined spatial distribution to predetermined distribution for at least one script-type to determine the script type of the text image.
摘要翻译：自动脚本确定装置自动确定文档的文本图像的总脚本类型。连接部件产生装置（28）从包括文本图像的像素生成连接的部件。边界盒生成装置（30）产生围绕每个连接的部件的边界盒。重心确定装置（32）确定每个边界盒的质心。脚本特征确定装置（34）针对每个边界盒确定相对于质心的一个或多个预定类型的特征的位置。脚本确定装置（36）确定整个文本图像的所定位的脚本特征的分布，并将确定的空间分布与至少一个脚本类型的预定分布进行比较，以确定文本图像的脚本类型。

98. 发明公开

EP0585944A2 Information processing method and apparatus 失效
标题翻译：信息处理方法和装置
公开(公告)号：EP0585944A2
公开(公告)日：1994-03-09
申请号：EP93114158.4
申请日：1993-09-03
申请人： CANON KABUSHIKI KAISHA
发明人： Arai, Tsunekazu, c/o Canon Kabushiki Kaisha , Sakaguchi, Katsuhiko, c/o Canon Kabushiki Kaisha , Mori, Shigeki, c/o Canon Kabushiki Kaisha , Matsubayashi, Kazuhiro, c/o Canon Kabushiki Kaisha , Harada, Takashi, c/o Canon Kabushiki Kaisha , Takasu, Eiji, c/o Canon Kabushiki Kaisha , Yoshii, Hiroto, c/o Canon Kabushiki Kaisha
IPC分类号： G06K9/64 , G06K9/03
CPC分类号： G06K9/6807 , G06K9/00429 , G06K9/6255
摘要： An information processing method including memorizing pattern information, memorizing use information of said pattern information memorized, and displaying said pattern information memorized and said use information of said pattern information.
摘要翻译：一种信息处理方法，包括存储图案信息，存储所存储的所述图案信息的使用信息，以及显示存储的所述图案信息和所述图案信息的所述使用信息。

99. 发明公开

EP0474364A3 Pattern matching apparatus 失效
标题翻译：图案匹配装置
公开(公告)号：EP0474364A3
公开(公告)日：1993-09-29
申请号：EP91307207.0
申请日：1991-08-06
申请人： GEC-MARCONI LIMITED
发明人： Webster, Simon Charles
IPC分类号： G06K9/82 , G06K9/68
CPC分类号： G06K9/82 , G06K9/6807
摘要： Apparatus for comparing an input genome sequence with one or more reference sequences comprises signal generators (10) for generating an input signal for each occurrence of each base component type (A,C,G,T) of the input sequence. A respective optical correlator (23-26) is provided for each base component type. Each correlator detects a match or near match between the occurrences of the respective base component type in the input sequence and the occurrences of that component type in any of the reference sequences, and produces a respective correlation signal. Decision-making circuitry (31) responds to the correlation signals from all of the correlators to provide an indication of a match or near match between the whole input sequence and any of the reference sequences.
摘要翻译：用于将输入基因组序列与一个或多个参考序列进行比较的装置包括用于为输入序列的每个基本分量类型（A，C，G，T）的每次出现产生输入信号的信号发生器（10）。为每个基本部件类型提供相应的光学相关器（23-26）。每个相关器检测输入序列中相应基本分量类型的出现与任何参考序列中该分量类型的出现之间的匹配或近似匹配，并产生相应的相关信号。决策电路（31）响应来自所有相关器的相关信号，以提供整个输入序列与任何参考序列之间的匹配或近似匹配的指示。

100. 发明公开

EP0546860A2 Character recognition 失效
标题翻译：字符识别
公开(公告)号：EP0546860A2
公开(公告)日：1993-06-16
申请号：EP92311352.6
申请日：1992-12-11
申请人： International Business Machines Corporation
发明人： Kitamura, Kozo
IPC分类号： G06K9/64
CPC分类号： G06K9/80 , G06K9/6807
摘要： In a character recognition system for recognising handwritten characters a predetermined characteristic amount is extracted for each stroke of a handwritten character, a characteristic amount word is created having one possibility of a binary value only in one or more bit positions corresponding to the characteristic amount, an AND operation (6) is performed bit-by-bit between the reference word of the corresponding stroke of the character of interest, and an OR operation is performed for all the bits of the results of the AND operation. If the number of binary values of the results of the OR operation for all the strokes of the character of interest exceeds a threshold, it is judged to be a candidate.
摘要翻译：在用于识别手写字符的字符识别系统中，为手写字符的每个笔划提取预定特征量，仅在对应于特征量的一个或多个位位置中创建具有二进制值的一种可能性的特征量字， AND操作（6）在感兴趣字符的相应笔划的参考字之间逐位执行，并且对AND操作的结果的所有位执行OR运算。如果感兴趣角色的所有笔画的或运算的结果的二进制值的数量超过阈值，则判断为候选者。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式