Title :
A novel image retrieval based on texture primitive
Author :
Jing, Liu ; Shan, Zhao
Author_Institution :
Sch. of Comput. Sci. & Technol., Henan Polytech. Univ., Jiaozuo, China
Abstract :
According to the block truncation coding (BTC), the texture primitive extracted from the image is used to describe the image texture feature. On the basis of which, an improved cooccurrence matrix and histogram are developed to extract the texture and shape features for the image retrieval. Experimental results have shown that the proposed method has sound and robust retrieval performance by integrating spatial and shape information into image texture descriptors.
Keywords :
block codes; image coding; image retrieval; image texture; block truncation coding; cooccurrence matrix; histogram; image retrieval; image texture feature; texture primitive; Color; Feature extraction; Histograms; Image color analysis; Image retrieval; Pixel; Shape; Co-occurrence matrix; Content-based image retrieval; Histigram; Key-block; Texture primitive;
Conference_Titel :
Computer Science and Education (ICCSE), 2010 5th International Conference on
Conference_Location :
Hefei
Print_ISBN :
978-1-4244-6002-1
DOI :
10.1109/ICCSE.2010.5593748