Title :
Image retrieval based on color-texture features of regions for MPEG-7
Author :
Qin, Tuanfa ; Li, Yue ; Huang, Wenyu ; Tang, Zhenhua
Author_Institution :
Sch. of Comput. & Electron. Inf., Guangxi Univ., Nanning, China
Abstract :
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, extraction and matching processes of features, and so on.
Keywords :
computer vision; content-based retrieval; feature extraction; image colour analysis; image matching; image retrieval; MPEG-7; color quantization; color-texture features; computer vision; content-based image retrieval; feature descriptors; feature extraction; feature matching; Color; Computer vision; Content based retrieval; Histograms; Image retrieval; Image segmentation; Information retrieval; MPEG 7 Standard; Quantization; Testing; content-based image retrieval; regional dominant color; regional edge histogram; similarity matrix;
Conference_Titel :
Network Infrastructure and Digital Content, 2009. IC-NIDC 2009. IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-4898-2
Electronic_ISBN :
978-1-4244-4900-6
DOI :
10.1109/ICNIDC.2009.5360826