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

US08265400B2 Identifying establishments in images 有权
标题翻译：识别图像中的场所
公开(公告)号：US08265400B2
公开(公告)日：2012-09-11
申请号：US13246812
申请日：2011-09-27
申请人： Tal Yadid , Yuval Netzer , Shlomo Urbach , Andrea Frome , Noam Ben-Haim
发明人： Tal Yadid , Yuval Netzer , Shlomo Urbach , Andrea Frome , Noam Ben-Haim
IPC分类号： G06K9/00
CPC分类号： G06K9/723 , G06F17/241 , G06F17/2705 , G06F17/30241 , G06K9/00664 , G06K2209/01
摘要： Establishments are identified in geo-tagged images. According to one aspect, text regions are located in a geo-tagged image and text strings in the text regions are recognized using Optical Character Recognition (OCR) techniques. Text phrases are extracted from information associated with establishments known to be near the geographic location specified in the geo-tag of the image. The text strings recognized in the image are compared with the phrases for the establishments for approximate matches, and an establishment is selected as the establishment in the image based on the approximate matches. According to another aspect, text strings recognized in a collection of geo-tagged images are compared with phrases for establishments in the geographic area identified by the geo-tags to generate scores for image-establishment pairs. Establishments in each of the large collection of images as well as representative images showing each establishment are identified using the scores.
摘要翻译：在地理标签图像中标识企业。根据一个方面，文本区域位于地理标记的图像中，并且使用光学字符识别（OCR）技术识别文本区域中的文本串。从与已知在图像的地理标签中指定的地理位置附近的企业相关联的信息中提取文本短语。将图像中识别的文本字符串与用于近似匹配的场所的短语进行比较，并且基于近似匹配来选择企业作为图像中的建立。根据另一方面，将在地理标签图像的集合中识别的文本字符串与由地理标签识别的地理区域中的企业的短语进行比较，以生成图像建立对的分数。使用分数来确定每个大图像集合中的各个场所以及显示每个机构的代表性图像。

2. 发明授权

US08385593B2 Selecting representative images for establishments 有权
公开(公告)号：US08385593B2
公开(公告)日：2013-02-26
申请号：US13105842
申请日：2011-05-11
申请人： Shlomo Urbach , Tal Yadid , Yuval Netzer , Andrea Frome , Noam Ben-Haim
发明人： Shlomo Urbach , Tal Yadid , Yuval Netzer , Andrea Frome , Noam Ben-Haim
IPC分类号： G06K9/00 , G06K9/18 , G06K9/68
CPC分类号： G06K9/723 , G06F17/241 , G06F17/2705 , G06F17/30241 , G06K9/00664 , G06K2209/01
摘要： Establishments are identified in geo-tagged images. According to one aspect, text regions are located in a geo-tagged image and text strings in the text regions are recognized using Optical Character Recognition (OCR) techniques. Text phrases are extracted from information associated with establishments known to be near the geographic location specified in the geo-tag of the image. The text strings recognized in the image are compared with the phrases for the establishments for approximate matches, and an establishment is selected as the establishment in the image based on the approximate matches. According to another aspect, text strings recognized in a collection of geo-tagged images are compared with phrases for establishments in the geographic area identified by the geo-tags to generate scores for image-establishment pairs. Establishments in each of the large collection of images as well as representative images showing each establishment are identified using the scores.

3. 发明申请

US20110311140A1 Selecting Representative Images for Establishments 有权
标题翻译：选择企业的代表性图像
公开(公告)号：US20110311140A1
公开(公告)日：2011-12-22
申请号：US13105842
申请日：2011-05-11
申请人： Shlomo Urbach , Tal Yadid , Yuval Netzer , Andrea Frome , Noam Ben-Haim
发明人： Shlomo Urbach , Tal Yadid , Yuval Netzer , Andrea Frome , Noam Ben-Haim
IPC分类号： G06K9/18
CPC分类号： G06K9/723 , G06F17/241 , G06F17/2705 , G06F17/30241 , G06K9/00664 , G06K2209/01
摘要： Establishments are identified in geo-tagged images. According to one aspect, text regions are located in a geo-tagged image and text strings in the text regions are recognized using Optical Character Recognition (OCR) techniques. Text phrases are extracted from information associated with establishments known to be near the geographic location specified in the geo-tag of the image. The text strings recognized in the image are compared with the phrases for the establishments for approximate matches, and an establishment is selected as the establishment in the image based on the approximate matches. According to another aspect, text strings recognized in a collection of geo-tagged images are compared with phrases for establishments in the geographic area identified by the geo-tags to generate scores for image-establishment pairs. Establishments in each of the large collection of images as well as representative images showing each establishment are identified using the scores.
摘要翻译：在地理标签图像中标识企业。根据一个方面，文本区域位于地理标记的图像中，并且使用光学字符识别（OCR）技术识别文本区域中的文本串。从与已知在图像的地理标签中指定的地理位置附近的企业相关联的信息中提取文本短语。将图像中识别的文本字符串与用于近似匹配的场所的短语进行比较，并且基于近似匹配来选择企业作为图像中的建立。根据另一方面，将在地理标签图像的集合中识别的文本字符串与由地理标签识别的地理区域中的企业的短语进行比较，以生成图像建立对的分数。使用分数来确定每个大图像集合中的各个场所以及显示每个机构的代表性图像。

4. 发明授权

US08532333B2 Selecting representative images for establishments 有权
标题翻译：为企业选择代表性图像
公开(公告)号：US08532333B2
公开(公告)日：2013-09-10
申请号：US13246809
申请日：2011-09-27
申请人： Shlomo Urbach , Tal Yadid , Yuval Netzer , Andrea Frome , Noam Ben-Haim
发明人： Shlomo Urbach , Tal Yadid , Yuval Netzer , Andrea Frome , Noam Ben-Haim
IPC分类号： G06K9/00
CPC分类号： G06K9/723 , G06F17/241 , G06F17/2705 , G06F17/30241 , G06K9/00664 , G06K2209/01
摘要： Establishments are identified in geo-tagged images. According to one aspect, text regions are located in a geo-tagged image and text strings in the text regions are recognized using Optical Character Recognition (OCR) techniques. Text phrases are extracted from information associated with establishments known to be near the geographic location specified in the geo-tag of the image. The text strings recognized in the image are compared with the phrases for the establishments for approximate matches, and an establishment is selected as the establishment in the image based on the approximate matches. According to another aspect, text strings recognized in a collection of geo-tagged images are compared with phrases for establishments in the geographic area identified by the geo-tags to generate scores for image-establishment pairs. Establishments in each of the large collection of images as well as representative images showing each establishment are identified using the scores.
摘要翻译：在地理标签图像中标识企业。根据一个方面，文本区域位于地理标记的图像中，并且使用光学字符识别（OCR）技术识别文本区域中的文本串。从与已知在图像的地理标签中指定的地理位置附近的企业相关联的信息中提取文本短语。将图像中识别的文本字符串与用于近似匹配的场所的短语进行比较，并且基于近似匹配来选择企业作为图像中的建立。根据另一方面，将在地理标签图像的集合中识别的文本字符串与由地理标签识别的地理区域中的企业的短语进行比较，以生成图像建立对的分数。使用分数来确定每个大图像集合中的各个场所以及显示每个机构的代表性图像。

5. 发明授权

US08379912B2 Identifying establishments in images 有权
标题翻译：识别图像中的场所
公开(公告)号：US08379912B2
公开(公告)日：2013-02-19
申请号：US13105853
申请日：2011-05-11
申请人： Tal Yadid , Yuval Netzer , Shlomo Urbach , Andrea Frome , Noam Ben-Haim
发明人： Tal Yadid , Yuval Netzer , Shlomo Urbach , Andrea Frome , Noam Ben-Haim
IPC分类号： G06K9/00
CPC分类号： G06K9/723 , G06F17/241 , G06F17/2705 , G06F17/30241 , G06K9/00664 , G06K2209/01
摘要： Establishments are identified in geo-tagged images. According to one aspect, text regions are located in a geo-tagged image and text strings in the text regions are recognized using Optical Character Recognition (OCR) techniques. Text phrases are extracted from information associated with establishments known to be near the geographic location specified in the geo-tag of the image. The text strings recognized in the image are compared with the phrases for the establishments for approximate matches, and an establishment is selected as the establishment in the image based on the approximate matches. According to another aspect, text strings recognized in a collection of geo-tagged images are compared with phrases for establishments in the geographic area identified by the geo-tags to generate scores for image-establishment pairs. Establishments in each of the large collection of images as well as representative images showing each establishment are identified using the scores.
摘要翻译：在地理标签图像中标识企业。根据一个方面，文本区域位于地理标记的图像中，并且使用光学字符识别（OCR）技术识别文本区域中的文本串。从与已知在图像的地理标签中指定的地理位置附近的企业相关联的信息中提取文本短语。将图像中识别的文本字符串与用于近似匹配的场所的短语进行比较，并且基于近似匹配来选择企业作为图像中的建立。根据另一方面，将在地理标签图像的集合中识别的文本字符串与由地理标签识别的地理区域中的企业的短语进行比较，以生成图像建立对的分数。使用分数来确定每个大图像集合中的各个场所以及显示每个机构的代表性图像。

6. 发明申请

US20120020565A1 Selecting Representative Images for Establishments 有权
标题翻译：选择企业的代表性图像
公开(公告)号：US20120020565A1
公开(公告)日：2012-01-26
申请号：US13246809
申请日：2011-09-27
申请人： Shlomo Urbach , Tal Yadid , Yuval Netzer , Andrea Frome , Noam Ben-Haim
发明人： Shlomo Urbach , Tal Yadid , Yuval Netzer , Andrea Frome , Noam Ben-Haim
IPC分类号： G06K9/18
CPC分类号： G06K9/723 , G06F17/241 , G06F17/2705 , G06F17/30241 , G06K9/00664 , G06K2209/01
摘要： Establishments are identified in geo-tagged images. According to one aspect, text regions are located in a geo-tagged image and text strings in the text regions are recognized using Optical Character Recognition (OCR) techniques. Text phrases are extracted from information associated with establishments known to be near the geographic location specified in the geo-tag of the image. The text strings recognized in the image are compared with the phrases for the establishments for approximate matches, and an establishment is selected as the establishment in the image based on the approximate matches. According to another aspect, text strings recognized in a collection of geo-tagged images are compared with phrases for establishments in the geographic area identified by the geo-tags to generate scores for image-establishment pairs. Establishments in each of the large collection of images as well as representative images showing each establishment are identified using the scores.
摘要翻译：在地理标签图像中标识企业。根据一个方面，文本区域位于地理标记的图像中，并且使用光学字符识别（OCR）技术识别文本区域中的文本串。从与已知在图像的地理标签中指定的地理位置附近的企业相关联的信息中提取文本短语。将图像中识别的文本字符串与用于近似匹配的场所的短语进行比较，并且基于近似匹配来选择企业作为图像中的建立。根据另一方面，将在地理标签图像的集合中识别的文本字符串与由地理标签识别的地理区域中的企业的短语进行比较，以生成图像建立对的分数。使用分数来确定每个大图像集合中的各个场所以及显示每个机构的代表性图像。

7. 发明申请

US20120121195A1 Identifying Establishments in Images 有权
标题翻译：识别图像中的企业
公开(公告)号：US20120121195A1
公开(公告)日：2012-05-17
申请号：US13105853
申请日：2011-05-11
申请人： Tal Yadid , Yuval Netzer , Shlomo Urbach , Andrea Frome , Noam Beh-Haim
发明人： Tal Yadid , Yuval Netzer , Shlomo Urbach , Andrea Frome , Noam Beh-Haim
IPC分类号： G06K9/72
CPC分类号： G06K9/723 , G06F17/241 , G06F17/2705 , G06F17/30241 , G06K9/00664 , G06K2209/01
摘要： Establishments are identified in geo-tagged images. According to one aspect, text regions are located in a geo-tagged image and text strings in the text regions are recognized using Optical Character Recognition (OCR) techniques. Text phrases are extracted from information associated with establishments known to be near the geographic location specified in the geo-tag of the image. The text strings recognized in the image are compared with the phrases for the establishments for approximate matches, and an establishment is selected as the establishment in the image based on the approximate matches. According to another aspect, text strings recognized in a collection of geo-tagged images are compared with phrases for establishments in the geographic area identified by the geo-tags to generate scores for image-establishment pairs. Establishments in each of the large collection of images as well as representative images showing each establishment are identified using the scores.
摘要翻译：在地理标签图像中标识企业。根据一个方面，文本区域位于地理标记的图像中，并且使用光学字符识别（OCR）技术识别文本区域中的文本串。从与已知在图像的地理标签中指定的地理位置附近的企业相关联的信息中提取文本短语。将图像中识别的文本字符串与用于近似匹配的场所的短语进行比较，并且基于近似匹配来选择企业作为图像中的建立。根据另一方面，将在地理标签图像的集合中识别的文本字符串与由地理标签识别的地理区域中的企业的短语进行比较，以生成图像建立对的分数。使用分数来确定每个大图像集合中的各个场所以及显示每个机构的代表性图像。

8. 发明申请

US20120020578A1 Identifying Establishments in Images 有权
公开(公告)号：US20120020578A1
公开(公告)日：2012-01-26
申请号：US13246812
申请日：2011-09-27
申请人： Tal Yadid , Yuval Netzer , Shlomo Urbach , Andrea Frome , Noam Beh-Haim
发明人： Tal Yadid , Yuval Netzer , Shlomo Urbach , Andrea Frome , Noam Beh-Haim
IPC分类号： G06K9/72
CPC分类号： G06K9/723 , G06F17/241 , G06F17/2705 , G06F17/30241 , G06K9/00664 , G06K2209/01
摘要： Establishments are identified in geo-tagged images. According to one aspect, text regions are located in a geo-tagged image and text strings in the text regions are recognized using Optical Character Recognition (OCR) techniques. Text phrases are extracted from information associated with establishments known to be near the geographic location specified in the geo-tag of the image. The text strings recognized in the image are compared with the phrases for the establishments for approximate matches, and an establishment is selected as the establishment in the image based on the approximate matches. According to another aspect, text strings recognized in a collection of geo-tagged images are compared with phrases for establishments in the geographic area identified by the geo-tags to generate scores for image-establishment pairs. Establishments in each of the large collection of images as well as representative images showing each establishment are identified using the scores.

9. 发明授权

US08509525B1 Clustering of forms from large-scale scanned-document collection 有权
标题翻译：从大型扫描文件收集中聚集表单
公开(公告)号：US08509525B1
公开(公告)日：2013-08-13
申请号：US13080877
申请日：2011-04-06
申请人： Shlomo Urbach , Eyal Fink , Tal Yadid , Yuval Netzer
发明人： Shlomo Urbach , Eyal Fink , Tal Yadid , Yuval Netzer
IPC分类号： G06K9/62
CPC分类号： G06K9/469 , G06K9/00449 , G06K9/00483 , G06K9/46 , G06K9/62 , G06K9/6224
摘要： Techniques for identifying documents sharing common underlying structures in a large collection of documents and processing the documents using the identified structures are disclosed. Images of the document collection are processed to detect occurrences of a predetermined set of image features that are common or similar among forms. The images are then indexed in an image index based on the detected image features. A graph of nodes is built. Nodes in the graph represent images and are connected to nodes representing similar document images by edges. Documents sharing common underlying structures are identified by gathering strongly inter-connected nodes in the graph. The identified documents are processed based at least in part on the resulting clusters.
摘要翻译：公开了用于识别在大量文档集合中共享共同底层结构的文档和使用所识别的结构处理文档的技术。处理文档集合的图像以检测形式之间共同或相似的预定图像特征集合的出现。然后基于检测到的图像特征将图像索引到图像索引中。构建节点图。图中的节点表示图像，并通过边缘连接到表示类似文档图像的节点。通过在图中收集强相互连接的节点来识别共享通用底层结构的文档。至少部分地基于所得到的集群来处理所识别的文档。

10. 发明授权

US08280891B1 System and method for the calibration of a scoring function 有权
标题翻译：用于校准功能的系统和方法
公开(公告)号：US08280891B1
公开(公告)日：2012-10-02
申请号：US13163014
申请日：2011-06-17
申请人： Shlomo Urbach , Yuval Netzer
发明人： Shlomo Urbach , Yuval Netzer
IPC分类号： G06F17/30
CPC分类号： G06F17/30705 , G06K2209/27
摘要： A system and method for calibrating a scoring function. The scoring function S(input, classification) provides a score based on the amount of evidence a particular input has in connection with a particular classification. For example, a street level image may be OCR'ed so as to indicate the names of establishments contained within the image, and the scoring function indicates how much evidence exists within the image for a particular establishment. Some establishments (i.e. classifications) may produce higher scores based on the nature of the establishment rather than the nature of the image (i.e. input) causing any ranking of establishments done on the basis of the scoring function to be biased. Accordingly, the scoring function is calibrated by determining the probability distribution of scores for an establishment over a false set of images that do not display the establishment. The scoring function is calibrated so as to adjust the score to overcome such bias.
摘要翻译：用于校准评分功能的系统和方法。评分函数S（输入，分类）基于特定输入与特定分类有关的证据量提供得分。例如，可以对街道图像进行OCR，以便指示图像中包含的场所的名称，并且评分函数指示针对特定机构的图像内存在多少证据。一些机构（即分类）可以基于建立的性质而不是图像的性质（即输入）产生更高的分数，从而导致基于评分函数完成的设施的任何排名被偏置。因此，通过确定不显示建立的虚拟图像集合上的企业的得分的概率分布来校准评分函数。评分功能被校准，以便调整分数以克服这种偏差。

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