Side-scan sonar image segmentation based on gray level co-occurrence matrices and unsupervised extreme learning machine

Side-scan sonar image segmentation is an important part in marine surveys, especially when we need to get the topographic features of the seabed. Actually, due to the complexity of the geomorphological characteristics in the seabed, we can't obtain any prior knowledge. Therefore we need an unsupervised system to segment side-scan sonar images automatically. In this paper, a novel segmentation system for side-scan sonar image based on Gray Level Co-occurrence Matrices (GLCM) and Unsupervised Extreme Learning Machine (US-ELM) is proposed. Experimental results demonstrate that the proposed method can get good segmentation.