A novel image retrieval based on texture primitive
Jing Liu, Shan Zhao · 2010
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.