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. 发明申请

US20130138685A1 Automatic Discovery of Popular Landmarks 有权
公开(公告)号：US20130138685A1
公开(公告)日：2013-05-30
申请号：US13619652
申请日：2012-09-14
申请人： Fernando A. Brucher , Ulrich Buddemeier , Hartwig Adam , Hartmut Neven
发明人： Fernando A. Brucher , Ulrich Buddemeier , Hartwig Adam , Hartmut Neven
IPC分类号： G06F17/30
CPC分类号： G06F17/30256 , G06F3/04842 , G06F7/08 , G06F17/30241 , G06F17/30253 , G06F17/30265 , G06F17/30268 , G06F17/3028 , G06K9/0063 , G06T7/97
摘要： In one embodiment the present invention is a method for populating and updating a database of images of landmarks including geo-clustering geo-tagged images according to geographic proximity to generate one or more geo-clusters, and visual-clustering the one or more geo-clusters according to image similarity to generate one or more visual clusters. In another embodiment, the present invention is a system for identifying landmarks from digital images, including the following components: a database of geo-tagged images; a landmark database; a geo-clustering module; and a visual clustering module. In other embodiments the present invention may be a method of enhancing user queries to retrieve images of landmarks, or a method of automatically tagging a new digital image with text labels.

2. 发明授权

US09014511B2 Automatic discovery of popular landmarks 有权
标题翻译：自动发现流行地标
公开(公告)号：US09014511B2
公开(公告)日：2015-04-21
申请号：US13619652
申请日：2012-09-14
申请人： Fernando A. Brucher , Ulrich Buddemeier , Hartwig Adam , Hartmut Neven
发明人： Fernando A. Brucher , Ulrich Buddemeier , Hartwig Adam , Hartmut Neven
IPC分类号： G06K9/54 , G06F17/30
CPC分类号： G06F17/30256 , G06F3/04842 , G06F7/08 , G06F17/30241 , G06F17/30253 , G06F17/30265 , G06F17/30268 , G06F17/3028 , G06K9/0063 , G06T7/97
摘要： In one embodiment the present invention is a method for populating and updating a database of images of landmarks including geo-clustering geo-tagged images according to geographic proximity to generate one or more geo-clusters, and visual-clustering the one or more geo-clusters according to image similarity to generate one or more visual clusters. In another embodiment, the present invention is a system for identifying landmarks from digital images, including the following components: a database of geo-tagged images; a landmark database; a geo-clustering module; and a visual clustering module. In other embodiments the present invention may be a method of enhancing user queries to retrieve images of landmarks, or a method of automatically tagging a new digital image with text labels.
摘要翻译：在一个实施例中，本发明是一种用于根据地理接近度来填充和更新包括地理聚类地理标记图像的地标图像的数据库的方法，以生成一个或多个地理群集，并且对一个或多个地理位置集群进行视觉聚类，根据图像相似性来生成一个或多个视觉集群。在另一个实施例中，本发明是一种用于从数字图像识别地标的系统，包括以下部件：地理标记图像的数据库; 一个地标数据库; 地理群集模块; 和视觉聚类模块。在其他实施例中，本发明可以是增强用户查询以检索地标图像的方法，或者是利用文本标签自动地标记新的数字图像的方法。

3. 发明授权

US08676001B2 Automatic discovery of popular landmarks 有权
标题翻译：自动发现流行地标
公开(公告)号：US08676001B2
公开(公告)日：2014-03-18
申请号：US12119359
申请日：2008-05-12
申请人： Fernando A. Brucher , Ulrich Buddemeier , Hartwig Adam , Hartmut Neven
发明人： Fernando A. Brucher , Ulrich Buddemeier , Hartwig Adam , Hartmut Neven
IPC分类号： G06K9/54
CPC分类号： G06F17/30256 , G06F3/04842 , G06F7/08 , G06F17/30241 , G06F17/30253 , G06F17/30265 , G06F17/30268 , G06F17/3028 , G06K9/0063 , G06T7/97
摘要： In one embodiment the present invention is a method for populating and updating a database of images of landmarks including geo-clustering geo-tagged images according to geographic proximity to generate one or more geo-clusters, and visual-clustering the one or more geo-clusters according to image similarity to generate one or more visual clusters. In another embodiment, the present invention is a system for identifying landmarks from digital images, including the following components: a database of geo-tagged images; a landmark database; a geo-clustering module; and a visual clustering module. In other embodiments the present invention may be a method of enhancing user queries to retrieve images of landmarks, or a method of automatically tagging a new digital image with text labels.
摘要翻译：在一个实施例中，本发明是一种用于根据地理接近度来填充和更新包括地理聚类地理标记图像的地标图像的数据库的方法，以生成一个或多个地理群集，并且对一个或多个地理位置集群进行视觉聚类，根据图像相似性来生成一个或多个视觉集群。在另一个实施例中，本发明是一种用于从数字图像识别地标的系统，包括以下部件：地理标记图像的数据库; 一个地标数据库; 地理群集模块; 和视觉聚类模块。在其他实施例中，本发明可以是增强用户查询以检索地标图像的方法，或者是利用文本标签自动地标记新的数字图像的方法。

4. 发明申请

US20090279794A1 Automatic Discovery of Popular Landmarks 有权
标题翻译：自动发现热门地标
公开(公告)号：US20090279794A1
公开(公告)日：2009-11-12
申请号：US12119359
申请日：2008-05-12
申请人： Fernando A. Brucher , Ulrich Buddemeier , Hartwig Adam , Hartmut Neven
发明人： Fernando A. Brucher , Ulrich Buddemeier , Hartwig Adam , Hartmut Neven
IPC分类号： G06K9/80
CPC分类号： G06F17/30256 , G06F3/04842 , G06F7/08 , G06F17/30241 , G06F17/30253 , G06F17/30265 , G06F17/30268 , G06F17/3028 , G06K9/0063 , G06T7/97
摘要： In one embodiment the present invention is a method for populating and updating a database of images of landmarks including geo-clustering geo-tagged images according to geographic proximity to generate one or more geo-clusters, and visual-clustering the one or more geo-clusters according to image similarity to generate one or more visual clusters. In another embodiment, the present invention is a system for identifying landmarks from digital images, including the following components: a database of geo-tagged images; a landmark database; a geo-clustering module; and a visual clustering module. In other embodiments the present invention may be a method of enhancing user queries to retrieve images of landmarks, or a method of automatically tagging a new digital image with text labels.
摘要翻译：在一个实施例中，本发明是一种用于根据地理接近度来填充和更新包括地理聚类地理标记图像的地标图像的数据库的方法，以生成一个或多个地理群集，并且对一个或多个地理位置集群进行视觉聚类，根据图像相似性来生成一个或多个视觉集群。在另一个实施例中，本发明是一种用于从数字图像识别地标的系统，包括以下部件：地理标记图像的数据库; 一个地标数据库; 地理群集模块; 和视觉聚类模块。在其他实施例中，本发明可以是增强用户查询以检索地标图像的方法，或者是利用文本标签自动地标记新的数字图像的方法。

5. 发明授权

US08761512B1 Query by image 有权
标题翻译：按图像查询
公开(公告)号：US08761512B1
公开(公告)日：2014-06-24
申请号：US12960413
申请日：2010-12-03
申请人： Ulrich Buddemeier , Gabriel Taubman , Hartwig Adam , Charles Rosenberg , Hartmut Neven , David Petrou , Fernando Brucher
发明人： Ulrich Buddemeier , Gabriel Taubman , Hartwig Adam , Charles Rosenberg , Hartmut Neven , David Petrou , Fernando Brucher
IPC分类号： G06K9/00
CPC分类号： G06F17/30277 , G06F17/30256 , G06F17/30268 , G06F17/3053 , G06F17/30554 , G06K9/6215 , G06K9/6282 , G06K9/723 , G06K2209/01
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing queries made up of images. In one aspect, a method includes indexing images by image descriptors. The method further includes associating descriptive n-grams with the images. In another aspect, a method includes receiving a query, identifying text describing the query, and performing a search according to the text identified for the query.
摘要翻译：方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于处理由图像组成的查询。一方面，一种方法包括通过图像描述符索引图像。该方法还包括将描述性n-gram与图像相关联。在另一方面，一种方法包括接收查询，识别描述查询的文本，以及根据为查询标识的文本执行搜索。

6. 发明授权

US08189964B2 Matching an approximately located query image against a reference image set 有权
标题翻译：将大致定位的查询图像与参考图像集进行匹配
公开(公告)号：US08189964B2
公开(公告)日：2012-05-29
申请号：US12632338
申请日：2009-12-07
申请人： John Flynn , Ulrich Buddemeier , Henrik Stewenius , Hartmut Neven , Fernando Brucher , Hartwig Adam
发明人： John Flynn , Ulrich Buddemeier , Henrik Stewenius , Hartmut Neven , Fernando Brucher , Hartwig Adam
IPC分类号： G06K9/36 , G06K9/62
CPC分类号： G06K9/00671 , G06F17/30241 , G06F17/30247 , G06K9/00704
摘要： Aspects of the invention pertain to matching a selected image/photograph against a database of reference images having location information. The image of interest may include some location information itself, such as latitude/longitude coordinates and orientation. However, the location information provided by a user's device may be inaccurate or incomplete. The image of interest is provided to a front end server, which selects one or more cells to match the image against. Each cell may have multiple images and an index. One or more cell match servers compare the image against specific cells based on information provided by the front end server. An index storage server maintains index data for the cells and provides them to the cell match servers. If a match is found, the front end server identifies the correct location and orientation of the received image, and may correct errors in an estimated location of the user device.
摘要翻译：本发明的方面涉及将选定的图像/照片与具有位置信息的参考图像的数据库进行匹配。感兴趣的图像可以包括一些位置信息本身，例如纬度/经度坐标和方向。然而，用户设备提供的位置信息可能不准确或不完整。感兴趣的图像被提供给前端服务器，前端服务器选择一个或多个单元以匹配图像。每个单元可以具有多个图像和索引。一个或多个单元匹配服务器根据前端服务器提供的信息将图像与特定单元进行比较。索引存储服务器维护单元的索引数据，并将它们提供给单元匹配服务器。如果找到匹配，则前端服务器识别接收到的图像的正确位置和方向，并且可以校正用户设备的估计位置中的错误。

7. 发明申请

US20110135207A1 Matching An Approximately Located Query Image Against A Reference Image Set 有权
标题翻译：将参考图像集合的大致位置查询图像进行匹配
公开(公告)号：US20110135207A1
公开(公告)日：2011-06-09
申请号：US12632338
申请日：2009-12-07
申请人： John Flynn , Ulrich Buddemeier , Henrik Stewenius , Hartmut Neven , Fernando Brucher , Hartwig Adam
发明人： John Flynn , Ulrich Buddemeier , Henrik Stewenius , Hartmut Neven , Fernando Brucher , Hartwig Adam
IPC分类号： G06K9/62
CPC分类号： G06K9/00671 , G06F17/30241 , G06F17/30247 , G06K9/00704
摘要： Aspects of the invention pertain to matching a selected image/photograph against a database of reference images having location information. The image of interest may include some location information itself, such as latitude/longitude coordinates and orientation. However, the location information provided by a user's device may be inaccurate or incomplete. The image of interest is provided to a front end server, which selects one or more cells to match the image against. Each cell may have multiple images and an index. One or more cell match servers compare the image against specific cells based on information provided by the front end server. An index storage server maintains index data for the cells and provides them to the cell match servers. If a match is found, the front end server identifies the correct location and orientation of the received image, and may correct errors in an estimated location of the user device.
摘要翻译：本发明的方面涉及将选定的图像/照片与具有位置信息的参考图像的数据库进行匹配。感兴趣的图像可以包括一些位置信息本身，例如纬度/经度坐标和方向。然而，用户设备提供的位置信息可能不准确或不完整。感兴趣的图像被提供给前端服务器，前端服务器选择一个或多个单元以匹配图像。每个单元可以具有多个图像和索引。一个或多个单元匹配服务器根据前端服务器提供的信息将图像与特定单元进行比较。索引存储服务器维护单元的索引数据，并将它们提供给单元匹配服务器。如果找到匹配，则前端服务器识别接收到的图像的正确位置和方向，并且可以校正用户设备的估计位置中的错误。

8. 发明申请

US20120114239A1 MATCHING AN APPROXIMATELY LOCATED QUERY IMAGE AGAINST A REFERENCE IMAGE SET 审中-公开
标题翻译：匹配对参考图像集的大致定位的查询图像
公开(公告)号：US20120114239A1
公开(公告)日：2012-05-10
申请号：US13352740
申请日：2012-01-18
申请人： John Flynn , Ulrich Buddemeier , Henrik Stewenius , Hartmut Neven , Fernando Brucher , Hartwig Adam
发明人： John Flynn , Ulrich Buddemeier , Henrik Stewenius , Hartmut Neven , Fernando Brucher , Hartwig Adam
IPC分类号： G06K9/68
CPC分类号： G06K9/00671 , G06F16/29 , G06F16/583 , G06F16/587 , G06K9/00704
摘要： Aspects of the invention pertain to matching a selected image/photograph against a database of reference images having location information. The image of interest may include some location information itself, such as latitude/longitude coordinates and orientation. However, the location information provided by a user's device may be inaccurate or incomplete. The image of interest is provided to a front end server, which selects one or more cells to match the image against. Each cell may have multiple images and an index. One or more cell match servers compare the image against specific cells based on information provided by the front end server. An index storage server maintains index data for the cells and provides them to the cell match servers. If a match is found, the front end server identifies the correct location and orientation of the received image, and may correct errors in an estimated location of the user device.
摘要翻译：本发明的方面涉及将选定的图像/照片与具有位置信息的参考图像的数据库进行匹配。感兴趣的图像可以包括一些位置信息本身，例如纬度/经度坐标和方向。然而，用户设备提供的位置信息可能不准确或不完整。感兴趣的图像被提供给前端服务器，前端服务器选择一个或多个单元以匹配图像。每个单元可以具有多个图像和索引。一个或多个单元匹配服务器根据前端服务器提供的信息将图像与特定单元进行比较。索引存储服务器维护单元的索引数据，并将它们提供给单元匹配服务器。如果找到匹配，则前端服务器识别接收到的图像的正确位置和方向，并且可以校正用户设备的估计位置中的错误。

9. 发明授权

US08086616B1 Systems and methods for selecting interest point descriptors for object recognition 有权
标题翻译：用于选择对象识别的兴趣点描述符的系统和方法
公开(公告)号：US08086616B1
公开(公告)日：2011-12-27
申请号：US12404857
申请日：2009-03-16
申请人： Alessandro Bissacco , Ulrich Buddemeier , Hartmut Neven
发明人： Alessandro Bissacco , Ulrich Buddemeier , Hartmut Neven
IPC分类号： G06F7/00
CPC分类号： G06K9/623
摘要： Systems and methods for selecting interest point descriptors for object recognition. In an embodiment, the present invention estimates performance of local descriptors by (1) receiving a local descriptor relating to an object in a first image; (2) identifying one or more nearest neighbor descriptors relating to one or more images different from the first image, the nearest neighbor descriptors comprising nearest neighbors of the local descriptor; (3) calculating a quality score for the local descriptor based on the number of nearest neighbor descriptors that relate to images showing the object; and (4) determining, on the basis of the quality score, if the local descriptor is effective in identifying the object.
摘要翻译：用于选择对象识别的兴趣点描述符的系统和方法。在一个实施例中，本发明通过（1）接收与第一图像中的对象有关的局部描述符来估计本地描述符的性能; （2）识别与不同于第一图像的一个或多个图像相关的一个或多个最近邻描述符，最近邻描述符包括本地描述符的最近邻; （3）基于与显示对象的图像相关的最近邻描述符的数量来计算本地描述符的质量得分; 以及（4）基于质量分数来确定本地描述符是否有效地识别对象。

10. 发明授权

US08995758B1 Classifying false positive descriptors 有权
标题翻译：分类假阳性描述符
公开(公告)号：US08995758B1
公开(公告)日：2015-03-31
申请号：US12489341
申请日：2009-06-22
申请人： Alessandro Bissacco , Ulrich Buddemeier , Hartmut Neven
发明人： Alessandro Bissacco , Ulrich Buddemeier , Hartmut Neven
IPC分类号： G06K9/62 , G06Q30/06
CPC分类号： G06Q30/06
摘要： According to an embodiment, a method for filtering descriptors for visual object recognition is provided. The method includes identifying false positive descriptors having a local match confidence that exceeds a predetermined threshold and a global image match confidence that is less than a second threshold. The method also includes training at least one classifier to discriminate between the false positive descriptors and other descriptors. The method further includes filtering feature point matches using the at least one classifier. According to another embodiment, the filtering step may further include removing one or more feature point matches from a result set. According to a further embodiment, a system for filtering feature point matches for visual object recognition is provided. The system includes a hard false positive identifier, a classifier trainer and a hard false positive filter.
摘要翻译：根据实施例，提供了一种用于过滤用于视觉对象识别的描述符的方法。该方法包括识别具有超过预定阈值的局部匹配置信度和小于第二阈值的全局图像匹配置信度的假阳性描述符。该方法还包括训练至少一个分类器以区分假阳性描述符和其他描述符。该方法还包括使用至少一个分类器来过滤特征点匹配。根据另一实施例，过滤步骤还可以包括从结果集中移除一个或多个特征点匹配。根据另一实施例，提供了一种用于过滤用于视觉对象识别的特征点匹配的系统。该系统包括硬假阳性标识符，分类器训练器和硬假阳性滤波器。

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