Image Retrieval Based on Spatial Feature of Texture Primitive
Shan Zhao, Hai-Xia Zhai · 2008
An image retrieval based on texture primitive is proposed in this paper. The texture primitive is firstly constructed according to the principle of the block truncation code (BTC). Meantime, based on the analysis of the statistical distribution of the texture primitive, the spatial distribution map of each feature is presented to describe the image texture information. Experimental results show that the proposed method has sound and robust retrieval performance by integrating spatial and texture information into image descriptors.