Image Retrieval Via Improved Relevance Ranking

摘要：

　　Recent years have witnessed the success of many online social media websites.Social images are usually associated with user-provided descriptors called tags,and thus tag-based search can be easily accomplished by using the descriptors as index terms.However,the existing methods frequently return results that are irrelevant or noisy with low-quality.It is argued that the relevance and quality are two important measures for a user friendly summarizing the returned images.In this paper,we propose a relevance-quality ranking method considering both image relevance and image quality.First,a relevance-based ranking scheme is utilized to automatically rank images according to their relevance to the query tag,which reckons the relevance scores based on both the visual similarity of images and the semantic consistency of associated tags.Then,quality scores are added to the candidate ranking list to accomplish the relevance-quality based ranking.Experimental results on NUS-WIDE image collection demonstrate the effectiveness of the proposed approach.

关键词： Tag-based image retrieval relevance ranking image quality visual similarity semantic consistency

作者: CHEN Lingling ZHU Songhao LI Zhuofan HU Juanjuan

作者单位: School of Automatic,Nanjing University of Post and Telecommunications,China

会议类型: 国际会议

会议名称: The 33th Chinese Control Conference第33届中国控制会议

会议地点: 南京

会议语种:英文

页码: 4620-4625

在线出版日期: 2014-07-28（万方平台首次上网日期，不代表论文的发表时间）