A comparative study of three moment-based shape descriptors

Shape is one of the fundamental visual features in the Content-based Image Retrieval (CBIR) paradigm. Numerous shape descriptors have been proposed in the literature. These can be broadly categorized as region-based and contour-based descriptors. Contour-based shape descriptors make use of only the boundary information, ignoring the shape interior content. Therefore, these descriptors cannot represent shapes for which the complete boundary information is not available. On the other hand, region-based descriptors exploit both boundary and internal pixels, and therefore are applicable to generic shapes. Among the region-based descriptors, moments have been very popular since they were first introduced in the 60's. In this paper we study and compare three moment-based descriptors: Invariant moments, Zernike moments, and radial Chebyshev moments. Experiments on the MPEG-7 shape databases show that radial Chebyshev moments achieve the highest retrieval performance.