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. 发明公开

EP0764308A1 SYSTEM AND METHOD FOR AUTOMATIC PAGE REGISTRATION AND AUTOMATIC ZONE DETECTION DURING FORMS PROCESSING 失效
标题翻译：系统和方法自动页面检测和形式检测
公开(公告)号：EP0764308A1
公开(公告)日：1997-03-26
申请号：EP96912690.0
申请日：1996-04-10
申请人： Rebus Technology, Inc.
发明人： RANGARAJAN, Vijayakumar c/o Parthasarathy,
IPC分类号： G06K9 , G06T3
CPC分类号： G06T3/608 , G06K9/2054 , G06K2209/01
摘要： A system and method automatically detect user defined zones in a document image of a form, compensating for skew and displacement of the image with respect to an original image of form. The system provides a mechanism to input an image for a form document, such as a scanner. The system processes the image to reduce its resolution and to remove significant skew. The image is presented to the user to define the zones. These zones are areas from which the user desires to extract meaningful data through optical character recognition, such as names, dates, addresses, and items on an invoice form. The system further processes the image to remove horizontal and vertical lines, and to create a number of blocks, representing either text or image data. The lines are removed and the blocks form by runlength smoothing with various parameters. The blocks form clusters of connected pixels. The blocks are labeled such that any set of connected blocks share a unique identification value. Additional data is collected on the commonly labeled blocks to select those blocks useful to definition of a template. The template is a collection of vectors between the centroids of each of the selected blocks. A second document image for processing is obtained, and similarly processed to minimize, deskew, and identify blocks and vectors therein. The vectors in the second document image are compared with vectors in a user selected template to determine the location of user defined zones in the second document image.

92. 发明授权

EP0436884B1 Verfahren zur Eingabe von Abtastzonen-Koordinaten bei automatischen Leseeinrichtungen für Briefe, Formulare o.ä. 失效
标题翻译：一种用于进入扫描区域法在自动读取设备坐标字母，表格或类似
公开(公告)号：EP0436884B1
公开(公告)日：1997-02-05
申请号：EP90124554.8
申请日：1990-12-18
申请人： Licentia Patent-Verwaltungs-GmbH
发明人： Hänsel, Karl-Günther, Dipl.-Phys.
IPC分类号： G06K9/32
CPC分类号： G06K9/033 , B07C3/10 , B07C3/20 , G06K9/2054 , G06K2209/01

93. 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.

94. 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。

95. 发明公开

EP0646887A2 Method and system for managing character recognition of a plurality of document form images having common data types 失效
标题翻译：方法和装置用于字符识别多个具有公共的数据类型形式的图像的管理。
公开(公告)号：EP0646887A2
公开(公告)日：1995-04-05
申请号：EP94114026.1
申请日：1994-09-07
申请人： International Business Machines Corporation
发明人： Billings, Douglas W.
IPC分类号： G06K9/20
CPC分类号： G06K9/2054 , G06K2209/01
摘要： A family of form types having a common set of data types, can be transformed into a meta-form which contains all of the data types which are arranged into a single layout. The location of the fields on the meta-form are specified by a meta-form definition data set. The single meta-form definition data set is substituted in a character recognition processor, for the plurality of form definition data sets which specify the layouts of the original form types in the family. This speeds the character recognition operation by not requiring a time consuming search for customized form definitions. Furthermore, by transforming the layout of field images for each form type in a family, into a single layout in the meta-form, the fields of the meta-form can be quickly located to speed the decompression of meaningful parts of the compressed document form image, without requiring the time consuming decompression of other parts which are not of interest.
摘要翻译：具有共同的一组数据类型的形式类型的家庭，可以转化成一个元形成包含所有被布置成一个单一的布局中的数据类型。元表格中的字段的位置是由一元格式定义数据集中指定。单元形式定义数据集是在字符识别处理器取代的，表单定义数据的多组其中在家庭指定原始形式类型的布局。这加快字符识别通过不需要耗时的搜索定制表单定义操作。进一步，通过在所述元形式转化场图像的布局中的一个家庭的每个形式类型，成一个单一的布局中，元形式的字段可以被快速地定位，以加速压缩文档形式的有意义的部分的解压缩图像，而不需要耗费哪些是不感兴趣的其他部位的减压时间。

96. 发明公开

EP0629970A3 Method for detecting monetary amounts in binary images 失效
标题翻译：一种用于检测在二进制图像金融量方法。
公开(公告)号：EP0629970A3
公开(公告)日：1995-03-15
申请号：EP94303833.1
申请日：1994-05-26
申请人： NCR International, Inc.
发明人： Kelland, Stewart B.
IPC分类号： G06K9/20
CPC分类号： G06K9/2054 , G06K2209/01
摘要： In a method of locating a monetary amount in a binary image, with a binary 1 representing a black pixel and a binary 0 representing a white pixel, an examining window (42) is positioned over a portion of the binary image and a list of objects is generated, with an object being defined as a set of contiguous black pixels. The objects are classified into parts such as characters, dots and commas, depending on predetermined criteria. The classified parts are then examined to determine whether or note they match a sequence which is indicative of a monetary amount. Then, the classified parts are examined to determine whether or not they conform to certain geometric criteria. Thus, a monetary amount is identified without effecting character recognition. The window (42) is moved to a next portion of data, and the process described is repeated.

97. 发明公开

EP0616296A3 Method and apparatus for processing documents 失效
标题翻译：为文档处理方法和装置。
公开(公告)号：EP0616296A3
公开(公告)日：1995-03-15
申请号：EP94301416.7
申请日：1994-02-28
申请人： NCR International, Inc.
发明人： Sharman, David B. , Zuckert, Derek
IPC分类号： G06K9/20
CPC分类号： G06Q40/02 , G06K9/00449 , G06K9/2054 , G06K2209/01 , G06Q20/042
摘要： In a method and apparatus for processing documents (30), a digital image of each document (30) is captured and stored in a memory (70). A feature model is formed from the stored image by extracting graphical features such as horizontal lines and/or boxes from the stored image, and this feature model is compared with stored feature models from an identification feature file (80) to identify the type of the document. The identification information is used to select, from a document definition file (82), an appropriate document description for identifying document zones to be read, and, from a library of image processing utilities (84), an appropriate processing utility, such as a data recognition utility to recognize the information read from such zones. The invention has an application to a self-service document processing terminal (10) for processing documents such as cheques (100) to be deposited or bills (150) to be paid.

98. 发明公开

EP0601107A4 METHOD AND APPARATUS FOR CONVERTING DOCUMENTS BETWEEN PAPER MEDIUM AND ELECTRONIC MEDIA. 失效
标题翻译：方法和设备纸张的电子媒体文档中实现。
公开(公告)号：EP0601107A4
公开(公告)日：1995-03-15
申请号：EP92919558
申请日：1992-08-28
申请人： TRW FINANCIAL SYSTEMS INC
发明人： LAWTON STEPHEN R , WARFEL GEORGE H JR
IPC分类号： G06F17/24 , G06F17/27 , G06K9/00 , G06K9/20
CPC分类号： G06F17/27 , G06F17/243 , G06K9/00 , G06K9/2054 , G06K2209/01
摘要： An apparatus and method for providing access to computerized information services for users unequipped with computers, particularly information services related to commercial transactions. Images of hardcopy forms are used as means for conveying transactional information. Each image contains character and data fields with information for a particular transaction. The system captures the image (22) and converts the character and data fields (24) into computer readable form. The system enhances each image (221) and performs several levels of feature extraction, including character recognition techniques (241). The system optimizes database lookup (2411) and human operator manual keying (245) to assist character recognition techniques in developing accurate coded text from the features of the image. The system produces accurate coded text strings for transmission (26) over telecommunications networks to independent computer systems. Additionally, user services provides processing of data received (29) from independent computer systems into management information.

99. 发明公开

EP0637811A2 Method for defining a plurality of form definition data sets 失效
标题翻译： Verfahren zum Definieren mehrererFormulardefinitionsdatensätze。
公开(公告)号：EP0637811A2
公开(公告)日：1995-02-08
申请号：EP94111380.5
申请日：1994-07-21
申请人： International Business Machines Corporation
发明人： Billings, Douglas W. , Burger, Mark E. , Pindell, Louis M.
IPC分类号： G06K9/20
CPC分类号： G06K9/2054 , G06K2209/01
摘要： A computer method enables a plurality of character recognition programs to recognize characters inscribed on a filled out version of the document form. The method enables a user to create a plurality of form definition data sets in a single working session, in a user friendly manner. It also enables the modification of form definition data sets in an easy, improved manner.
摘要翻译：一种计算机方法使得多个字符识别程序可以识别在文档形式的填写版本上刻录的字符。该方法使得用户能够以用户友好的方式在单个工作会话中创建多个表单定义数据集。它还能够以简单，改进的方式修改表单定义数据集。

100. 发明公开

EP0632402A1 Method for image segmentation and classification of image elements for document processing 失效
标题翻译： Verfahren zum Segmentieren von Bildern und Klassifizieren von Bildelementen zur Dokumentverarbeitung。
公开(公告)号：EP0632402A1
公开(公告)日：1995-01-04
申请号：EP93110476.4
申请日：1993-06-30
申请人： International Business Machines Corporation
发明人： Rindtorff, Klaus
IPC分类号： G06K9/34 , G06K9/20
CPC分类号： G06K9/00442 , G06K9/00154 , G06K9/2054 , G06K9/342 , G06K9/346 , G06K2209/01
摘要： A method to segment, classify and clean an image is presented. It may be used in applications which have image data as their input that contains different classes of elements. The method will find, separate and classify those elements. Only significant elements must be kept for further processing and thus the amount of processed data may be significantly reduced.
摘要翻译：提出了一种分割，分类和清理图像的方法。它可以用于具有包含不同类别元素的图像数据作为其输入的应用中。该方法将找到，分离和分类这些元素。必须保留重要的元素用于进一步处理，因此可以显着减少处理数据的数量。

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