Underwater Image Segmentation Combining Dual-Band Enhancing and Edge-Grouping

In order to make segmentation more robust and accurate in the underwater environment, a two-stage segmentation method is proposed in this paper. In preprocessing stage, a dual-band enhancing technique is used to preserve the target contour and at the same time eliminate the fake edges generated by the noises; in segmentation stage, edge-grouping method is chosen for its advantageous characteristics over noisy images. Experimental results show that the proposed method can get a better performance both in stability and accuracy.