Statistical Landscape Features for Texture Retrieval

A method of using information derived from the graph of an image function for texture description is proposed in this paper. The graph of an image function is a surface in the three-dimensional space that appears like a landscape. Four texture feature curves based on the statistics of geometrical and topological properties of the solids induced by the graph and a variable horizontal plane are used to characterize the texture. This method is named statistical landscape features (SLF). Systematic experimental comparison using the Brodatz texture set as well as the VisTex texture set shows that the performance of the proposed statistical landscape features is higher than that of multi-resolution simultaneous auto-regressive, statistical geometrical features and discrete wavelet transform.