会议专题

IMAGE RETRIEVAL BASED ON COLOR-TEXTURE FEATURES OF REGIONS FOR MPEG-7

Content-based image retrieval is an important research topic in computer vision. MPEG-7 set up a set of standardized description of image contents. By introducing the widely used feature descriptors, we analyze the limitation and deficiency of retrieval methods based on global features in this paper. Meanwhile, an image retrieval approach based on integrated features of regions for MPEG-7 is put forward to meet users requirements of evaluating similarity on spatial information. The availability of our approach is testified through retrieval experiments. This paper also describes our approach in detail on color quantization, exaction and matching processes of features, and so on.

content-based image retrieval regional dominant color regional edge histogram similarity matriz

Tuanfa Qin Yue Li Wenyu Huang Zhenhua Tang

School of Computer and Electronic Information, Guangxi University, Nanning, Guangxi 530004, China

国际会议

2009 IEEE International Conference on Network Infrastructure and Digital Content(2009年IEEE网络基础设施与数字内容国际会议 IEEE IC-NIDC2009)

北京

英文

456-460

2009-11-06(万方平台首次上网日期,不代表论文的发表时间)