Image segmentation based on 2D OTSU and simplified swarm optimization

Jianjia Pan, Xianwei Zheng, Li Sun, Lina Yang, Yulong Wang, Huiwu Luo, Patrick Shen-Pei Wang

Abstract: Image segmentation is a classic problem and basic research area in image processing. It can provide pre-detect information for subsequent image processing and classification. 2D Otsu method is a widely used non-parametric method to detect the threshold of image. In this paper, we employ the simplified swarm optimization (SSO) as a swarm-intelligent optimization method to search the threshold value based on 2D Otsu method. Experimental result has shown that the proposed method could consume less computation time of 2D Otsu method and achieve the optimal value.