Image retrieval systems and methods with semantic

专利名称：Image retrieval systems and methods with

semantic and feature based relevancefeedback

发明人：Wen-Yin Liu,Hong-Jiang Zhang,Ye Lu申请号：US09702292申请日：20001030公开号：US07099860B1公开日：20060829

专利附图：

摘要：An image retrieval system performs both keyword-based and content-basedimage retrieval. A user interface allows a user to specify queries using a combination of

keywords and examples images. Depending on the input query, the image retrievalsystem finds images with keywords that match the keywords in the query and/or imageswith similar low-level features, such as color, texture, and shape. The system ranks theimages and returns them to the user. The user interface allows the user to identifyimages that are more relevant to the query, as well as images that are less or notrelevant to the query. The user may alternatively elect to refine the search by selectingone example image from the result set and submitting its low-level features in a newquery. The image retrieval system monitors the user feedback and uses it to refine anysearch efforts and to train itself for future search queries. In the describedimplementation, the image retrieval system seamlessly integrates feature-basedrelevance feedback and semantic-based relevance feedback.

申请人：Wen-Yin Liu,Hong-Jiang Zhang,Ye Lu

地址：Beijing CN,Beijing CN,Burnaby CA

国籍：CN,CN,CA

代理机构：Lee & Hayes, PLLC

更多信息请下载全文后查看