Classification of underwater objects based on Zernike and pseudo Zernike moments and Fourier descriptors

Abstract

In this work the process of classification of underwater objects in sonar images is treated. The necessary steps, which are based on image processing and computer vision, are first the segmentation, then feature extraction and finally classification. Three different kinds of descriptors are tested in this work: the Zernike Polynomials (ZP), the pseudo Zernike Polynomials (PZP) and the Fourier Descriptors (FD). Several sets of these coefficients are tested with a Mahalanobis classifier. A set of coefficients are proposed that give us succesful results for each feature descriptor and there are compared to choose the most reliable.