Perceptive visual texture classification and retrieval

Abstract

We present some analysis techniques and indexing strategies aimed to support classification and retrieval of textures using only perceptual features. The goal of this research is to provide a visual system that, starting from graphical cues representing relevant perceptual features of texture, interactively searches the most similar texture in the set of candidates in the corresponding texture space. Hence, a set of relevant perceptual features, used for indexing, is proposed: directionality, contrast and coarseness. A graphical representation of the computed characteristics is presented together with some examples. Finally, texture retrieval experiments using such iconic representations are presented and discussed.