专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明授权

US08452099B2 Optical character recognition (OCR) engines having confidence values for text types 有权
标题翻译：具有文本类型置信度的光学字符识别（OCR）引擎
公开(公告)号：US08452099B2
公开(公告)日：2013-05-28
申请号：US12954865
申请日：2010-11-27
申请人： Prakash Reddy
发明人： Prakash Reddy
IPC分类号： G06K9/00
CPC分类号： G06K9/6255 , G06K9/6292 , G06K2209/01
摘要： An image of a known text sample having a text type is generated. The image of the known text sample is input into each OCR engine of a number of OCR engines. Output text corresponding to the image of the known text sample is received from each OCR engine. For each OCR engine, the output text received from the OCR engine is compared with the known text sample, to determine a confidence value of the OCR engine for the text type of the known text sample.
摘要翻译：生成具有文本类型的已知文本样本的图像。已知文本样本的图像被输入到多个OCR引擎的每个OCR引擎中。从每个OCR引擎接收与已知文本样本的图像相对应的输出文本。对于每个OCR引擎，将从OCR引擎接收的输出文本与已知的文本样本进行比较，以确定OCR引擎对已知文本样本的文本类型的置信度值。

32. 发明授权

US08413037B2 User selection of flaw present within digitally scanned document 有权
标题翻译：用户选择数字扫描文档中存在的缺陷
公开(公告)号：US08413037B2
公开(公告)日：2013-04-02
申请号：US12824201
申请日：2010-06-27
申请人： Craig P. Sayers , Prakash Reddy
发明人： Craig P. Sayers , Prakash Reddy
IPC分类号： G06K9/40
CPC分类号： G06F17/30011 , H04N1/00005 , H04N1/00074 , H04N1/00408 , H04N1/00411 , H04N1/0044
摘要： A page of a digitally scanned document and graphical user interface elements (GUI) are displayed. Each GUI element corresponds to a potential flaw within the page and includes an example image of the potential flaw. After the GUI elements are displayed, a user is permitted to select a user-detected flaw present within the page of the digitally scanned document by selecting one of the GUI elements.
摘要翻译：显示数字扫描文档和图形用户界面元素（GUI）的页面。每个GUI元素对应于页面内的潜在缺陷并且包括潜在缺陷的示例图像。在显示GUI元素之后，允许用户通过选择GUI元素中的一个来选择在数字扫描文档的页面内存在的用户检测到的缺陷。

33. 发明授权

US08326078B2 System and method for removing artifacts from a digitized document 有权
标题翻译：从数字化文档中删除工件的系统和方法
公开(公告)号：US08326078B2
公开(公告)日：2012-12-04
申请号：US12360807
申请日：2009-01-27
申请人： Prakash Reddy , Jian Fan , Steven T. Rosenberg
发明人： Prakash Reddy , Jian Fan , Steven T. Rosenberg
IPC分类号： G06K9/40 , G06K9/36
CPC分类号： G06K9/346
摘要： A system and method is disclosed for removing artifacts from a digitized document. The method discloses receiving a digitized document, having an image format, and including content and an artifact; identifying a content boundary within the digitized document; enhancing the digitized document after identifying the content boundary; and removing the artifact by cropping the digitized document to the content boundary after enhancing the digitized document The system discloses a processor configured to operate a series of functional modules, including: a means for receiving a digitized document, having an image format, and including content and an artifact; a content boundary identification module, for identifying a content boundary within the digitized document; an image enhancement module, for enhancing the digitized document after identifying the content boundary; and a content cropping module, for removing the artifact by cropping the digitized document to the content boundary after enhancing the digitized document.
摘要翻译：公开了一种用于从数字化文档中去除伪影的系统和方法。该方法公开接收具有图像格式并包括内容和伪影的数字化文档; 识别数字化文档内的内容边界; 识别内容边界后增强数字化文件; 并且在增强数字化文档之后通过将数字化文档裁剪到内容边界来去除该伪影。该系统公开了一种配置成操作一系列功能模块的处理器，包括：用于接收具有图像格式并包括内容的数字化文档的装置和神器; 内容边界识别模块，用于识别所述数字化文档内的内容边界; 图像增强模块，用于在识别内容边界之后增强数字化文档; 以及内容裁剪模块，用于通过在增强数字化文档之后将数字化文档裁剪到内容边界来去除该伪像。

34. 发明授权

US08266542B2 Rendering and sorting book search results as three dimensional icons 有权
标题翻译：将图书搜索结果作为三维图标进行渲染和排序
公开(公告)号：US08266542B2
公开(公告)日：2012-09-11
申请号：US12817724
申请日：2010-06-17
申请人： Craig Peter Sayers , Prakash Reddy , Prabodh Tiwari
发明人： Craig Peter Sayers , Prakash Reddy , Prabodh Tiwari
IPC分类号： G06F3/048 , G06F15/177 , G06F3/00
CPC分类号： G06F17/30991 , G06F3/04815
摘要： Illustrated is a system and method to prepare for display, within a Graphical User Interface (GUI), a subset selection pane, an icon and summary pane, and a sort pane. The system and method further to include to prepare for display, within the icon and summary pane, a result set that includes an icon representing a three dimensional book and a textual summary of the book. The system and method also includes enabling a screen object, within the subset selection pane, to receive input to select a subset of the result set to be displayed within the icon and summary pane. Further, the system and method includes enabling a screen object, within the sort pane, to receive input to select the subset of the result set to be sorted and displayed within the icon and summary pane.
摘要翻译：说明的是在图形用户界面（GUI），子集选择窗格，图标和摘要窗格以及排序窗格中准备显示的系统和方法。所述系统和方法进一步包括以在图标和摘要窗格内准备显示包括表示三维书籍的图标和本书的文本摘要的结果集。该系统和方法还包括使得子集选择窗格内的屏幕对象能够接收输入以选择要在图标和摘要窗格内显示的结果集的子集。此外，该系统和方法包括使得分类窗格内的屏幕对象能够接收输入以选择要在图标和摘要窗格内排序和显示的结果集的子集。

35. 发明申请

US20120020561A1 METHOD AND SYSTEM FOR OPTICAL CHARACTER RECOGNITION USING IMAGE CLUSTERING 有权
标题翻译：使用图像聚类的光学字符识别的方法和系统
公开(公告)号：US20120020561A1
公开(公告)日：2012-01-26
申请号：US12841839
申请日：2010-07-22
申请人： Kave Eshghi , George Forman , Prakash Reddy
发明人： Kave Eshghi , George Forman , Prakash Reddy
IPC分类号： G06K9/34
CPC分类号： G06K9/00463
摘要： The present disclosure provides a computer-implemented method of translating an image-based electronic document into a text-based electronic document. The method includes electronically scanning an image-based document to determine positions of word images in the image-based document. The method also includes extracting the word images from the image-based document and storing the word images to an electronic storage device. The method also includes grouping a subset of the word images into a word cluster based on a similarity of the word images, wherein the word images in the word cluster correspond to a same actual word. The method also includes generating a character-encoded transcription for the word cluster based on the word images in the word cluster. The method also includes adding the character-encoded transcription to a text-based electronic document at locations corresponding to the positions of the word images in the image-based document.
摘要翻译：本公开提供了一种将基于图像的电子文档翻译成基于文本的电子文档的计算机实现的方法。该方法包括电子扫描基于图像的文档以确定基于图像的文档中的单词图像的位置。该方法还包括从基于图像的文档提取单词图像并将单词图像存储到电子存储设备。该方法还包括基于单词图像的相似性将单词图像的子集分组成单词群集，其中单词群集中的单词图像对应于相同的实际单词。该方法还包括基于单词簇中的单词图像生成用于单词群集的字符编码的转录。该方法还包括在基于图像的文档中与单词图像的位置对应的位置处将字符编码的转录添加到基于文本的电子文档。

36. 发明申请

US20110314411A1 RENDERING AND SORTING BOOK SEARCH RESULTS AS THREE DIMENSIONAL ICONS 有权
标题翻译：渲染和分类书搜索结果作为三维图形
公开(公告)号：US20110314411A1
公开(公告)日：2011-12-22
申请号：US12817724
申请日：2010-06-17
申请人： Craig Peter SAYERS , Prakash Reddy , Prabodh Tiwari
发明人： Craig Peter SAYERS , Prakash Reddy , Prabodh Tiwari
IPC分类号： G06F3/048
CPC分类号： G06F17/30991 , G06F3/04815
摘要： Illustrated is a system and method to prepare for display, within a Graphical User Interface (GUI), a subset selection pane, an icon and summary pane, and a sort pane. The system and method further to include to prepare for display, within the icon and summary pane, a result set that includes an icon representing a three dimensional book and a textual summary of the book. The system and method also includes enabling a screen object, within the subset selection pane, to receive input to select a subset of the result set to be displayed within the icon and summary pane. Further, the system and method includes enabling a screen object, within the sort pane, to receive input to select the subset of the result set to be sorted and displayed within the icon and summary pane.
摘要翻译：说明的是在图形用户界面（GUI），子集选择窗格，图标和摘要窗格以及排序窗格中准备显示的系统和方法。所述系统和方法进一步包括以在图标和摘要窗格内准备显示包括表示三维书籍的图标和本书的文本摘要的结果集。该系统和方法还包括使得子集选择窗格内的屏幕对象能够接收输入以选择要在图标和摘要窗格内显示的结果集的子集。此外，该系统和方法包括使得分类窗格内的屏幕对象能够接收输入以选择要在图标和摘要窗格内排序和显示的结果集的子集。

37. 发明申请

US20100225937A1 IMAGED PAGE WARP CORRECTION 审中-公开
标题翻译：成像页面温度校正
公开(公告)号：US20100225937A1
公开(公告)日：2010-09-09
申请号：US12399333
申请日：2009-03-06
申请人： Steven J. Simske , Andrew Bolwell , Jian Fan , Timothy Louis Kohler , Prakash Reddy , Steven T. Rosenberg
发明人： Steven J. Simske , Andrew Bolwell , Jian Fan , Timothy Louis Kohler , Prakash Reddy , Steven T. Rosenberg
IPC分类号： G06F15/00 , H04N1/40 , G06K9/40 , G06K9/36
CPC分类号： G06K9/3283 , H04N1/387
摘要： A method of correcting warp on an imaged page includes generating projection profiles for pixels on the imaged page and determining a reference baseline based on the projection profiles; calculating a deviation away from the reference baseline for points along a boundary; and mapping the points along the boundary to the reference baseline.
摘要翻译：校正成像页面上的翘曲的方法包括：生成成像页面上的像素的投影轮廓，并基于投影轮廓确定参考基线; 计算沿边界点的参考基准偏差; 并将沿着边界的点映射到参考基线。

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