Textural Segmentation of Sidescan Sonar Images Based on Gabor Filters Bank and Active Contours without Edges

Abstract

This work deals with textural segmenting of high resolution sidescan sonar images by using active contours and Gabor filters. In fact this method is a modification of Chan and Vese Active contour model. It makes the method suitable for textural segmenting of above said images. First, image is passed through a symmetric bank of Gabor filters. Then, filtered images that possess a significant component of the original image are subjected to morphological closing operator. At the end, we use multi channel C-V active contour model for segmenting areas with different textures. Results of the proposed method are presented for different real and simulated sidescan sonar images to demonstrate the robustness of it.