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. 发明申请

US20140250109A1 RERANKING USING CONFIDENT IMAGE SAMPLES 有权
标题翻译：使用保密的图像样本进行快照
公开(公告)号：US20140250109A1
公开(公告)日：2014-09-04
申请号：US13393509
申请日：2011-11-24
申请人： Jingdong Wang , Shipeng Li , Nobuyuki Morioka
发明人： Jingdong Wang , Shipeng Li , Nobuyuki Morioka
IPC分类号： G06F17/30
CPC分类号： G06F17/3053 , G06F17/30247 , G06F17/30256 , G06F17/30268 , G06F17/30277
摘要： The techniques described herein determine an initial set of ranked images associated with an image-based search query. Based on visual content similarities between images in the initial set of ranked images, the techniques select confident image samples from the initial set of ranked images. The techniques then use the confident image samples to rerank the initial set of ranked images. Accordingly, a search engine uses the confident image samples to promote images that are likely to be relevant to the search query, while demoting images that are not likely to be relevant to the search query. Therefore, the search engine can provide improved relevance-based search results to an image-based search query.
摘要翻译：本文描述的技术确定与基于图像的搜索查询相关联的初始的排序图像集合。基于初始设置的图像中的图像之间的视觉内容相似性，该技术从初始的排列图像集中选择可信度图像样本。然后，技术使用自信的图像样本重新排列初始的排序图像集。因此，搜索引擎使用确定的图像样本来推广可能与搜索查询相关的图像，同时降低与搜索查询不可能相关的图像。因此，搜索引擎可以向基于图像的搜索查询提供改进的基于关联的搜索结果。

32. 发明授权

US08705870B2 Image searching by approximate κ-NN graph 有权
标题翻译：图像搜索近似＆kgr; -NN图
公开(公告)号：US08705870B2
公开(公告)日：2014-04-22
申请号：US13411213
申请日：2012-03-02
申请人： Jingdong Wang , Shipeng Li , Jing Wang
发明人： Jingdong Wang , Shipeng Li , Jing Wang
IPC分类号： G06K9/50 , G06K9/34 , G06K9/54
CPC分类号： G06F17/30247
摘要： This disclosure describes techniques for searching for similar images to an image query by using an approximate k-Nearest Neighbor (k-NN) graph. The approximate k-NN graph is constructed from data points partitioned into subsets to further identify nearest-neighboring data points for each data point. The data points may connect with the nearest-neighboring data points in a subset to form an approximate neighborhood subgraph. These subgraphs from all the subsets are combined together to form a base approximate k-NN graph. Then by performing more random hierarchical partition, more base approximate k-NN graphs are formed, and further combined together to create an approximate k-NN graph. The approximate k-NN graph expands into other neighborhoods and identifies the best k-NN data points. The approximate k-NN graph retrieves the best NN data points, based at least in part on the retrieved best k-NN data points representing images being similar in appearance to the image query.
摘要翻译：本公开描述了通过使用近似k最近邻（k-NN）图来搜索图像查询的类似图像的技术。从划分成子集的数据点构建近似k-NN图，以进一步识别每个数据点的最近邻数据点。数据点可以与子集中的最邻近的数据点连接，以形成大致的邻域子图。来自所有子集的这些子图被组合在一起以形成基本的近似k-NN图。然后通过执行更多的随机分层分区，形成更多的基本近似k-NN图，并进一步组合在一起以创建一个近似的k-NN图。近似的k-NN图扩展到其他邻域，并识别最佳的k-NN数据点。至少部分地基于检索出的最佳k-NN数据点，近似k-NN图形检索出最佳的NN数据点，该数据点表示与图像查询相似的图像。

33. 发明申请

US20130230255A1 Image Searching By Approximate k-NN Graph 有权
标题翻译：通过近似k-NN图进行图像搜索
公开(公告)号：US20130230255A1
公开(公告)日：2013-09-05
申请号：US13411213
申请日：2012-03-02
申请人： Jingdong Wang , Shipeng Li , Jing Wang
发明人： Jingdong Wang , Shipeng Li , Jing Wang
IPC分类号： G06K9/46
CPC分类号： G06F17/30247
摘要： This disclosure describes techniques for searching for similar images to an image query by using an approximate k-Nearest Neighbor (k-NN) graph. The approximate k-NN graph is constructed from data points partitioned into subsets to further identify nearest-neighboring data points for each data point. The data points may connect with the nearest-neighboring data points in a subset to form an approximate neighborhood subgraph. These subgraphs from all the subsets are combined together to form a base approximate k-NN graph. Then by performing more random hierarchical partition, more base approximate k-NN graphs are formed, and further combined together to create an approximate k-NN graph. The approximate k-NN graph expands into other neighborhoods and identifies the best k-NN data points. The approximate k-NN graph retrieves the best NN data points, based at least in part on the retrieved best k-NN data points representing images being similar in appearance to the image query.
摘要翻译：本公开描述了通过使用近似k最近邻（k-NN）图来搜索图像查询的类似图像的技术。从划分成子集的数据点构建近似k-NN图，以进一步识别每个数据点的最近邻数据点。数据点可以与子集中的最邻近的数据点连接，以形成大致的邻域子图。来自所有子集的这些子图被组合在一起以形成基本的近似k-NN图。然后通过执行更多的随机分层分区，形成更多的基本近似k-NN图，并进一步组合在一起以创建一个近似的k-NN图。近似的k-NN图扩展到其他邻域，并识别最佳的k-NN数据点。至少部分地基于检索出的最佳k-NN数据点，近似k-NN图形检索出最佳的NN数据点，该数据点表示与图像查询相似的图像。

34. 发明申请

US20120162244A1 IMAGE SEARCH COLOR SKETCH FILTERING 审中-公开
标题翻译：图像搜索彩色草图过滤
公开(公告)号：US20120162244A1
公开(公告)日：2012-06-28
申请号：US12980071
申请日：2010-12-28
申请人： YUE MA , JUSTIN DAVID Hamilton , Gong Cheng , Jingdong Wang
发明人： YUE MA , JUSTIN DAVID Hamilton , Gong Cheng , Jingdong Wang
IPC分类号： G09G5/02 , G06K9/68
CPC分类号： G06F16/532
摘要： Visual features of images are translated into visual words defined by a dictionary. The visual words are indexed and the images are stored in an image store. A sketched imaged, translated into visual words, is utilized to search for similar images in the image store. The visual words are compared to visual words in the index to identify matches associated with stored images. The stored images are displayed and ranked according to the highest number of matches. Textual searches are used to supplement or refine the search results.
摘要翻译：图像的视觉特征被翻译成由词典定义的视觉词。视觉词被索引，图像存储在图像存储中。被绘制成图像，被翻译为视觉词，被用于在图像存储中搜索类似的图像。将视觉词与索引中的视觉词进行比较，以识别与存储的图像相关联的匹配。存储的图像根据最高匹配数量进行显示和排序。文字搜索用于补充或改进搜索结果。

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