A comparative study of invariant descriptors for shape retrieval

This paper presents a comparative study between scale, rotation and translation invariant descriptors for shape representation and retrieval. Specifically, we studied Fourier, angular radial transform and image moment descriptors for shape representation. Since shape is one of the most widely used image feature exploited in content-based image retrieval systems, we studied for each descriptor, the number of coefficients needed for indexing and their retrieval performance. Results showed that moment descriptors present the best performance in both terms of shape representation quality as well as in the amount of required coefficients.