专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08693779B1 Segmenting printed media pages into articles 有权
标题翻译：将印刷媒体页面分割成文章
公开(公告)号：US08693779B1
公开(公告)日：2014-04-08
申请号：US13612072
申请日：2012-09-12
申请人： Ankur Jain , Vivek Sahasranaman , Shobhit Saxena , Krishnendu Chaudhury
发明人： Ankur Jain , Vivek Sahasranaman , Shobhit Saxena , Krishnendu Chaudhury
IPC分类号： G06K9/34 , G06K9/46 , G06K9/66
CPC分类号： G06K9/00463
摘要： Methods and systems for segmenting printed media pages into individual articles quickly and efficiently. A printed media based image that may include a variety of columns, headlines, images, and text is input into the system which comprises a block segmenter and an article segmenter system. The block segmenter identifies and produces blocks of textual content from a printed media image while the article segmenter system determines which blocks of textual content belong to one or more articles in the printed media image based on a classifier algorithm. A method for segmenting printed media pages into individual articles is also presented.
摘要翻译：将印刷媒体页面快速有效地分割成单个文章的方法和系统。将包括各种列，标题，图像和文本的基于印刷媒体的图像输入到包括块分割器和物品分割器系统的系统中。块分割器基于分类器算法，从打印媒体图像识别并产生文本内容块，同时文章分割器系统基于分类器算法确定文本内容的哪些块属于打印的媒体图像中的一个或多个文章。还介绍了将打印的媒体页面分割成单个文章的方法。

2. 发明申请

US20080126415A1 Digital Image Archiving and Retrieval in a Mobile Device System 有权
标题翻译：移动设备系统中的数字图像归档和检索
公开(公告)号：US20080126415A1
公开(公告)日：2008-05-29
申请号：US11564823
申请日：2006-11-29
申请人： Krishnendu Chaudhury , Ashutosh Garg , Prasenjit Phukan , Arvind Saraf
发明人： Krishnendu Chaudhury , Ashutosh Garg , Prasenjit Phukan , Arvind Saraf
IPC分类号： G06F17/30
CPC分类号： G06F17/30253 , G06K9/6857
摘要： A computer-implemented method of managing information is disclosed. The method can include receiving a message from a mobile device configured to connect to a mobile device network (the message including a digital image taken by the mobile device and including information corresponding to words), determining the words from the digital image information using optical character recognition, indexing the digital image based on the words, and storing the digital image for later retrieval of the digital image based on one or more received search terms.
摘要翻译：公开了一种管理信息的计算机实现方法。该方法可以包括从配置成连接到移动设备网络的移动设备接收消息（该消息包括由移动设备拍摄的数字图像并且包括与单词对应的信息），使用光学字符从数字图像信息中确定单词识别，基于这些字索引数字图像，以及存储数字图像以便随后检索数字图像，基于一个或多个所接收的搜索项。

3. 发明授权

US08755595B1 Automatic extraction of character ground truth data from images 有权
标题翻译：从图像中自动提取字符地面真值数据
公开(公告)号：US08755595B1
公开(公告)日：2014-06-17
申请号：US13186173
申请日：2011-07-19
申请人： Alessandro Bissacco , Krishnendu Chaudhury
发明人： Alessandro Bissacco , Krishnendu Chaudhury
IPC分类号： G06K9/62
CPC分类号： G06K9/6256
摘要： Embodiments for automatic extraction of character ground truth data from images are disclosed. A transcription may be rendered in a plurality of fonts and orientations to obtain a set of candidate word templates with associated character bounding boxes. A word template may be selected from the set of candidate word templates, wherein the selected word template corresponds to a word patch from an image. The character bounding boxes, of the selected word template, may be evaluated in a plurality of orientations about each respective character from the word patch to obtain a set of candidate character templates. For each respective character from the word patch, a character template may be selected from the set of candidate character templates, wherein each selected character template corresponds to the respective character from the word patch. Character ground truth data comprising the selected character templates oriented to correspond to the word patch, may be provided as training data for recognizing the characters of the word patch from the image.
摘要翻译：公开了从图像自动提取字符地面真值数据的实施例。可以以多个字体和取向呈现转录，以获得具有相关联的字符边界框的一组候选词模板。可以从候选词模板集中选择单词模板，其中所选择的单词模板对应于来自图像的单词补丁。所选择的单词模板的字符边界框可以从关于每个相应字符的多个方向从单词补丁中求出，以获得一组候选字符模板。对于来自单词补丁的每个相应字符，可以从候选字符模板集合中选择字符模板，其中每个所选字符模板对应于来自字补丁的相应字符。可以将包括定向为对应于单词补丁的所选择的字符模板的角色地面真实数据提供为用于从图像识别单词补丁的字符的训练数据。

4. 发明授权

US08290268B2 Segmenting printed media pages into articles 有权
标题翻译：将印刷媒体页面分割成文章
公开(公告)号：US08290268B2
公开(公告)日：2012-10-16
申请号：US12191120
申请日：2008-08-13
申请人： Ankur Jain , Vivek Sahasranaman , Shobhit Saxena , Krishnendu Chaudhury
发明人： Ankur Jain , Vivek Sahasranaman , Shobhit Saxena , Krishnendu Chaudhury
IPC分类号： G06K9/34
CPC分类号： G06K9/00463
摘要： Methods and systems for segmenting printed media pages into individual articles quickly and efficiently. A printed media based image that may include a variety of columns, headlines, images, and text is input into the system which comprises a block segmenter and a article segmenter system. The block segmenter identifies and produces blocks of textual content from a printed media image while the article segmenter system determines which blocks of textual content belong to one or more articles in the printed media image based on a classifier algorithm. A method for segmenting printed media pages into individual articles is also presented.
摘要翻译：将印刷媒体页面快速有效地分割成单个文章的方法和系统。可以将包括各种列，标题，图像和文本的基于印刷媒体的图像输入到包括块分割器和物品分割器系统的系统中。块分割器基于分类器算法，从打印媒体图像识别并产生文本内容块，同时文章分割器系统基于分类器算法确定文本内容的哪些块属于打印的媒体图像中的一个或多个文章。还介绍了将打印的媒体页面分割成单个文章的方法。

5. 发明申请

US20110274373A1 Digital Image Archiving and Retrieval in a Mobile Device System 有权
标题翻译：移动设备系统中的数字图像归档和检索
公开(公告)号：US20110274373A1
公开(公告)日：2011-11-10
申请号：US13181263
申请日：2011-07-12
申请人： Krishnendu Chaudhury , Ashutosh Garg , Prasenjit Phukan , Arvind Saraf
发明人： Krishnendu Chaudhury , Ashutosh Garg , Prasenjit Phukan , Arvind Saraf
IPC分类号： G06K9/20
CPC分类号： G06F17/30253 , G06K9/6857
摘要： A computer-implemented method of managing information is disclosed. The method can include receiving a message from a mobile device configured to connect to a mobile device network (the message including a digital image taken by the mobile device and including information corresponding to words), determining the words from the digital image information using optical character recognition, indexing the digital image based on the words, and storing the digital image for later retrieval of the digital image based on one or more received search terms.
摘要翻译：公开了一种管理信息的计算机实现方法。该方法可以包括从配置成连接到移动设备网络的移动设备接收消息（该消息包括由移动设备拍摄的数字图像并且包括与单词对应的信息），使用光学字符从数字图像信息中确定单词识别，基于这些字索引数字图像，以及存储数字图像以便随后检索数字图像，基于一个或多个所接收的搜索项。

6. 发明授权

US08218913B1 Identifying a front page in media material 有权
标题翻译：识别媒体资料中的首页
公开(公告)号：US08218913B1
公开(公告)日：2012-07-10
申请号：US12190176
申请日：2008-08-12
申请人： Sriram Thirthala , Krishnendu Chaudhury
发明人： Sriram Thirthala , Krishnendu Chaudhury
IPC分类号： G06K9/00
CPC分类号： G06K9/00483
摘要： The present invention relates to systems and methods for identifying front pages from images representing media. In an embodiment, a system for identifying at least one front page within an image representing media is provided. The system includes a matcher, an aggregator and a reviewer. In another embodiment, a method for identifying at least one front page within an image representing media is provided. The method includes comparing each page to matching criteria to produce a matching confidence score. The method also includes aggregating, as front page candidates, each page having a matching confidence score that exceeds a matching confidence score threshold. The method further includes receiving decision information and identifying front pages from front page candidates based upon the decision information. According to another embodiment, the matching criteria may comprise at least one local, affine invariant feature point.
摘要翻译：本发明涉及用于从表示媒体的图像中识别首页的系统和方法。在一个实施例中，提供了一种用于识别表示媒体的图像内的至少一个前页的系统。该系统包括匹配器，聚合器和审阅者。在另一个实施例中，提供了一种用于识别代表媒体的图像内的至少一个前页的方法。该方法包括将每个页面与匹配标准进行比较以产生匹配的置信度分数。该方法还包括作为首页候选者聚合具有超过匹配置信度分数阈值的匹配置信度分数的每个页面。所述方法还包括基于所述决定信息接收决策信息和从首页候选中识别前端页面。根据另一个实施例，匹配标准可以包括至少一个局部仿射不变特征点。

7. 发明授权

US07813582B1 Method and apparatus for enhancing object boundary precision in an image 有权
标题翻译：用于增强图像中物体边界精度的方法和装置
公开(公告)号：US07813582B1
公开(公告)日：2010-10-12
申请号：US11527294
申请日：2006-09-25
申请人： Krishnendu Chaudhury , Ashutosh Kulshreshtha
发明人： Krishnendu Chaudhury , Ashutosh Kulshreshtha
IPC分类号： G06K9/40 , G06K9/00
CPC分类号： G06T5/003 , G06T2207/10024 , G06T2207/20192
摘要： One embodiment of the present invention provides a system that enhances sharpness of object boundaries in an image. During operation, the system first receives an image. Next, the system computes gradients of color values for pixels in the image. The system then computes displacement vectors for pixels in the image, wherein the magnitude of the displacement vector for a given pixel is proportional to the magnitude of the gradient of the color value at the given pixel. The system next replaces the color values for the pixels, wherein the color value for a given pixel is replaced with a color value obtained from a location at the end of the displacement vector for the given pixel.
摘要翻译：本发明的一个实施例提供一种提高图像中物体边界的清晰度的系统。在操作期间，系统首先接收图像。接下来，系统计算图像中像素的颜色值的梯度。系统然后计算图像中的像素的位移矢量，其中给定像素的位移矢量的大小与给定像素处的颜色值的梯度的大小成比例。系统接下来替换像素的颜色值，其中给定像素的颜色值被替换为从给定像素的位移矢量的结尾处的位置获得的颜色值。

8. 发明授权

US07986843B2 Digital image archiving and retrieval in a mobile device system 有权
标题翻译：移动设备系统中的数字图像归档和检索
公开(公告)号：US07986843B2
公开(公告)日：2011-07-26
申请号：US11564823
申请日：2006-11-29
申请人： Krishnendu Chaudhury , Ashutosh Garg , Prasenjit Phukan , Arvind Saraf
发明人： Krishnendu Chaudhury , Ashutosh Garg , Prasenjit Phukan , Arvind Saraf
IPC分类号： G06K9/72
CPC分类号： G06F17/30253 , G06K9/6857
摘要： A computer-implemented method of managing information is disclosed. The method can include receiving a message from a mobile device configured to connect to a mobile device network (the message including a digital image taken by the mobile device and including information corresponding to words), determining the words from the digital image information using optical character recognition, indexing the digital image based on the words, and storing the digital image for later retrieval of the digital image based on one or more received search terms.
摘要翻译：公开了一种管理信息的计算机实现方法。该方法可以包括从配置成连接到移动设备网络的移动设备接收消息（该消息包括由移动设备拍摄的数字图像并且包括与单词对应的信息），使用光学字符从数字图像信息中确定单词识别，基于这些字索引数字图像，以及存储数字图像以便随后检索数字图像，基于一个或多个所接收的搜索项。

9. 发明授权

US08620114B2 Digital image archiving and retrieval in a mobile device system 有权
标题翻译：移动设备系统中的数字图像归档和检索
公开(公告)号：US08620114B2
公开(公告)日：2013-12-31
申请号：US13181263
申请日：2011-07-12
申请人： Krishnendu Chaudhury , Ashutosh Garg , Prasenjit Phukan , Arvind Saraf
发明人： Krishnendu Chaudhury , Ashutosh Garg , Prasenjit Phukan , Arvind Saraf
IPC分类号： G06K9/20
CPC分类号： G06F17/30253 , G06K9/6857
摘要： A computer-implemented method of managing information is disclosed. The method can include receiving a message from a mobile device configured to connect to a mobile device network (the message including a digital image taken by the mobile device and including information corresponding to words), determining the words from the digital image information using optical character recognition, indexing the digital image based on the words, and storing the digital image for later retrieval of the digital image based on one or more received search terms.
摘要翻译：公开了一种管理信息的计算机实现方法。该方法可以包括从配置成连接到移动设备网络的移动设备接收消息（该消息包括由移动设备拍摄的数字图像并且包括与单词对应的信息），使用光学字符从数字图像信息中确定单词识别，基于这些字索引数字图像，以及存储数字图像以便随后检索数字图像，基于一个或多个所接收的搜索项。

10. 发明申请

US20100040287A1 Segmenting Printed Media Pages Into Articles 有权
标题翻译：将印刷媒体页面分割成文章
公开(公告)号：US20100040287A1
公开(公告)日：2010-02-18
申请号：US12191120
申请日：2008-08-13
申请人： Ankur Jain , Vivek Sahasranaman , Shobhit Saxena , Krishnendu Chaudhury
发明人： Ankur Jain , Vivek Sahasranaman , Shobhit Saxena , Krishnendu Chaudhury
IPC分类号： G06K9/34
CPC分类号： G06K9/00463
摘要： Methods and systems for segmenting printed media pages into individual articles quickly and efficiently. A printed media based image that may include a variety of columns, headlines, images, and text is input into the system which comprises a block segmenter and a article segmenter system. The block segmenter identifies and produces blocks of textual content from a printed media image while the article segmenter system determines which blocks of textual content belong to one or more articles in the printed media image based on a classifier algorithm. A method for segmenting printed media pages into individual articles is also presented.
摘要翻译：将印刷媒体页面快速有效地分割成单个文章的方法和系统。可以将包括各种列，标题，图像和文本的基于印刷媒体的图像输入到包括块分割器和物品分割器系统的系统中。块分割器基于分类器算法，从打印媒体图像识别并产生文本内容块，同时文章分割器系统基于分类器算法确定文本内容的哪些块属于打印的媒体图像中的一个或多个文章。还介绍了将打印的媒体页面分割成单个文章的方法。

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