-
公开(公告)号：US08594431B2
公开(公告)日：2013-11-26
申请号：US13617106
申请日：2012-09-14
申请人： Ami Ben-Horesh , Amir Geva , Eugeniusz Walach
发明人： Ami Ben-Horesh , Amir Geva , Eugeniusz Walach
CPC分类号： G06K9/346 , G06K9/6203 , G06K9/685 , G06K2209/01
摘要： A method and system for recognizing a character affected by a noise or an obstruction is disclosed. After receiving an image with characters, a character being affected by a noise or an obstruction is determined. Then, areas in the character where the noise or obstruction affected are precisely located. Templates representing every possible character in the image are updated by removing equivalent areas to the areas in the character being affected by the noise or obstruction. Then, the character is classified in a template among the updated templates by finding the template having the highest number of matching pixels with the character.
摘要翻译： 公开了一种用于识别受噪声或障碍影响的字符的方法和系统。 在接收到具有字符的图像之后，确定受噪声或障碍物影响的字符。 然后，噪音或障碍受影响的人物中的区域精确定位。 表示图像中每个可能字符的模板通过移除受噪声或障碍影响的字符区域的等效区域进行更新。 然后，通过找到具有该字符的匹配像素数最多的模板，将该字符分类到更新的模板中的模板中。
-
公开(公告)号：US20130011067A1
公开(公告)日：2013-01-10
申请号：US13617106
申请日：2012-09-14
申请人： Ami Ben-Horesh , Amir Geva , Eugeniusz Walach
发明人： Ami Ben-Horesh , Amir Geva , Eugeniusz Walach
IPC分类号： G06K9/00
CPC分类号： G06K9/346 , G06K9/6203 , G06K9/685 , G06K2209/01
摘要： A method and system for recognizing a character affected by a noise or an obstruction is disclosed. After receiving an image with characters, a character being affected by a noise or an obstruction is determined. Then, areas in the character where the noise or obstruction affected are precisely located. Templates representing every possible character in the image are updated by removing equivalent areas to the areas in the character being affected by the noise or obstruction. Then, the character is classified in a template among the updated templates by finding the template having the highest number of matching pixels with the character.
摘要翻译： 公开了一种用于识别受噪声或障碍影响的字符的方法和系统。 在接收到具有字符的图像之后，确定受噪声或障碍物影响的字符。 然后，噪音或障碍受影响的人物中的区域精确定位。 表示图像中每个可能字符的模板通过移除受噪声或障碍影响的字符区域的等效区域进行更新。 然后，通过找到具有该字符的匹配像素数最多的模板，将该字符分类到更新的模板中的模板中。
-
公开(公告)号：US08116567B2
公开(公告)日：2012-02-14
申请号：US12246626
申请日：2008-10-07
申请人： Asaf Tzadok , Eugeniusz Walach
发明人： Asaf Tzadok , Eugeniusz Walach
CPC分类号： G06K9/00442 , G06K2209/01
摘要： Techniques for performing page verification of a document are provided. The techniques include performing a recognition technique on a document to recognize one or more objects in the document, excluding the one or more recognized objects from the document, and performing page verification of the document, wherein page verification comprises visual inspection of the document excluding the one or more recognized objects.
摘要翻译： 提供用于执行文档的页面验证的技术。 这些技术包括在文档上执行识别技术以识别文档中的一个或多个对象，从文档中排除一个或多个识别的对象，以及执行文档的页面验证，其中页面验证包括不包括文档的文档的目视检查 一个或多个识别的对象。
-
4.发明申请公开(公告)号：US20090273597A1
公开(公告)日：2009-11-05
申请号：US12115018
申请日：2008-05-05
申请人： Kashyap K. Chatamballi , Tal Drory , Amir Geva , Eugeniusz Walach
发明人： Kashyap K. Chatamballi , Tal Drory , Amir Geva , Eugeniusz Walach
IPC分类号： G06F17/00
CPC分类号： G06F11/3692
摘要： A technique is disclosed for the performance of application software “screen layout” testing analysis by designation of “fiduciary blocks” (e.g., words, boxes etc.) to serve as geometrical features for identification of data fields of interest viewed within a graphical user interface (GUI) screen. The set of designated “geometric fiduciary blocks” is then assembled into a “hierarchical structure” to analyze test results involving the data fields contained within each block.
摘要翻译： 公开了一种用于通过指定“受信块”（例如，字，框等）来执行应用软件“屏幕布局”测试分析的技术，以用作识别在图形用户界面中观看的感兴趣的数据字段的几何特征 （GUI）屏幕。 然后将该组指定的“几何受信块”组装成“分层结构”，以分析涉及每个块内包含的数据字段的测试结果。
-
公开(公告)号：US20090263019A1
公开(公告)日：2009-10-22
申请号：US12103717
申请日：2008-04-16
申请人： Asaf Tzadok , Eugeniusz WALACH
发明人： Asaf Tzadok , Eugeniusz WALACH
IPC分类号： G06K9/34
CPC分类号： G06K9/00852 , G06K9/6255
摘要： Disclosed embodiments of the invention provide automated global optimization methods and systems of OCR, tailored to each document being digitized. A document-specific database is created from an OCR scan of a document of interest, which contains an exhaustive listing of words in the document. Images of each word, taken from all the fonts encountered, are entered into the database and mapped to a corresponding textual representation. After entry of a first instance of an image of a word written in a particular font, each new occurrence of the word in that font can be quickly recognized by image processing techniques. The disclosed methods and systems may be used in conjunction with adaptive character recognition training and word recognition training of the OCR engines.
摘要翻译： 本发明的公开的实施例提供针对正被数字化的每个文档的自动化全局优化方法和OCR系统。 从文档的OCR扫描创建文档特定的数据库，其中包含文档中单词的详尽列表。 从遇到的所有字体中取出的每个单词的图像都将输入到数据库中，并映射到相应的文本表示。 在以特定字体写入的单词的图像的第一实例输入之后，可以通过图像处理技术快速识别该字体中的单词的新出现。 所公开的方法和系统可以与OCR引擎的自适应字符识别训练和字识别训练结合使用。
-
公开(公告)号：US20090208059A1
公开(公告)日：2009-08-20
申请号：US12033899
申请日：2008-02-20
IPC分类号： G06K9/00
CPC分类号： G06K9/3258 , G06K2209/15 , G08G1/017 , G08G1/14
摘要： A method for identifying vehicles, including capturing a first image of a first vehicle using a first camera at a first position and a second image of the first vehicle using a second camera at a second position different from the first position. The method further includes determining a transformation between the first image and the second image. A third image of a second vehicle using the first camera is captured, and the transformation is applied to the third image to generate a fourth image of the second vehicle. The fourth image is analyzed, using a database of identified vehicles, to determine an identity of the second vehicle.
摘要翻译： 一种用于识别车辆的方法，包括使用第一车辆的第一照相机在第一位置捕获第一车辆的第一图像，并且使用第二照相机在与第一位置不同的第二位置处拍摄第一车辆的第二图像。 该方法还包括确定第一图像和第二图像之间的变换。 捕获使用第一照相机的第二车辆的第三图像，并且将变换应用于第三图像以生成第二车辆的第四图像。 使用识别的车辆的数据库分析第四图像，以确定第二车辆的身份。
-
7.发明授权Point of sale system with item image capture and deferred invoicing capability 有权具有物品图像捕获和延期开票功能的销售点系统公开(公告)号：US08818875B2
公开(公告)日：2014-08-26
申请号：US12235605
申请日：2008-09-23
申请人： Ehud Dov Karnin , Eugeniusz Walach
发明人： Ehud Dov Karnin , Eugeniusz Walach
IPC分类号： G07G5/00
CPC分类号： G06Q30/04 , A47F9/047 , G06Q20/208 , G06Q20/209 , G06Q30/06 , G07G1/0063
摘要： A novel and useful mechanism and method for processing transactions on a point of sale system comprising of a conveyor system which continuously moves when one ore more items or items are resting on the conveyor system, and a sensing system to capture the information necessary to identify the items on the conveyor. When all items are correctly recognized by the sensing devices, the customer is charged for the items and an invoice is printed. In the event all the items are not correctly recognized the captured information is forwarded to a remote location for automated recognition processing and manual identification, if necessary. Once all the items are successfully identified, the customer is charged for the purchase and an invoice is processed and sent to the customer.
摘要翻译： 一种用于在销售点系统处理交易的新颖有用的机构和方法，包括当一个或多个物品搁置在输送机系统上时连续移动的输送机系统;以及感测系统，用于捕获识别 输送机上的物品 当所有物品被感测装置正确识别时，客户将收取物品的费用并打印发票。 如果所有项目未正确识别，必要时将捕获的信息转发到远程位置进行自动识别处理和手动识别。 一旦所有项目都被成功识别，客户将被要求购买，发票已处理并发送给客户。
-
公开(公告)号：US07607078B2
公开(公告)日：2009-10-20
申请号：US11176503
申请日：2005-07-06
申请人： Amir Geva , Ehud Karnin , Eugeniusz Walach
发明人： Amir Geva , Ehud Karnin , Eugeniusz Walach
IPC分类号： G06F17/00
CPC分类号： G06Q10/10
摘要： A method for processing forms in a computer system includes receiving from a human operator a design of a unified from template including data fields and respective attributes. Paper forms and electronic forms (e-forms) are automatically produced based on the unified form template. Filled-in paper forms and filled-in e-forms are accepted from the clients of the computer system, the filled-in forms including data items filled into the respective data fields by the clients. The data items are extracted from the filled-in paper forms and the filled-in e-forms responsively to the unified form template.
摘要翻译： 一种用于在计算机系统中处理表单的方法包括从人类操作员接收包括数据字段和相应属性的模板的统一设计。 纸张形式和电子表单（电子表格）将根据统一表格模板自动生成。 从计算机系统的客户接受填写的纸质表格和填写的电子表格，填写的表格包括客户填写到各个数据字段中的数据项。 数据项是从填写的纸张形式和填写的电子表格中提取出来的，响应于统一表单模板。
-
9.发明申请System, Method and Computer Program Product for Performing Information Transfer Using a Virtual Operator 审中-公开使用虚拟操作器执行信息传输的系统，方法和计算机程序产品公开(公告)号：US20080001959A1
公开(公告)日：2008-01-03
申请号：US11426949
申请日：2006-06-28
申请人： Amir Geva , Eugeniusz Walach
发明人： Amir Geva , Eugeniusz Walach
IPC分类号： G06F13/00
摘要： A system, computer program product and a method for performing information transfer, the method includes: executing, by a virtual operator, a first set of input operations such as to cause a computerized system to generate first image information representative of a first image; analyzing the first image information and in response to the analysis performing a second set of input operations required to complete an information transfer operation associated with the computerize system; and analyzing second image information generated by the computerized system in response to the execution of the second set of input operation in order to validate a completion of the information transfer operation.
摘要翻译： 一种用于执行信息传送的系统，计算机程序产品和方法，所述方法包括：由虚拟操作者执行第一组输入操作，使得计算机化系统生成表示第一图像的第一图像信息; 分析第一图像信息并且响应于执行完成与计算机化系统相关联的信息传送操作所需的第二组输入操作的分析; 以及响应于所述第二组输入操作的执行来分析由所述计算机化系统生成的第二图像信息，以便验证所述信息传送操作的完成。
-
公开(公告)号：US20070154098A1
公开(公告)日：2007-07-05
申请号：US11325039
申请日：2006-01-04
申请人： Amir Geva , Ehud Karnin , Eugeniusz Walach
发明人： Amir Geva , Ehud Karnin , Eugeniusz Walach
CPC分类号： G06F17/243 , G06K9/2063 , G06K17/0003 , G06K2209/01
摘要： A computer-implemented method for processing paper forms includes accepting a filled-in paper form conforming to a template at a computer system having a local memory, wherein the template is not stored in the local memory. Identification information is extracted from the filled-in paper form using the computer system. The identification information indicates a network address of a remote storage location external to the computer system, in which the template is stored. The template is retrieved responsively to the identification information by communication with the remote storage location via a wide area network (WAN). The filled-in paper form is processed responsively to the retrieved template.
摘要翻译： 用于处理纸张形式的计算机实现的方法包括在具有本地存储器的计算机系统处接受符合模板的填写纸张形式，其中模板不存储在本地存储器中。 使用计算机系统从填写的纸张表单中提取识别信息。 识别信息表示存储模板的计算机系统外部的远程存储位置的网络地址。 通过经由广域网（WAN）与远程存储位置通信来响应于标识信息来检索模板。 响应于检索的模板处理填写的纸张表单。
-
-
-
-
-
-
-
-
-
搜索结果
42 条记录 (耗时 0.016 秒)