Brachiopods classification based on fusion of contour and region based descriptors

Abstract

In this paper, we propose a contour-region based shape descriptor for Brachiopods classification by using a combinations of Fourier descriptors and R-transform extracted from Radon transform. Fourier descriptors is supported by the well-developed and well-understood Fourier theory and are a powerful features for the recognition of two-dimensional connected shapes. We used the stable and complete Fourier descriptors proposed by Ghorbel to present the contour information. To depict shape interior content we used the R-transform. It is advantages lies in its low computational complexity and geometric invariance. We compared the proposed descriptor with curvature scale space, R-transform and Ghorbel descriptors using city block distance measure and our Brachiopods database. We present the experimental results to reveal the performance of the proposed descriptor which is independent on the starting points and efficient.