Improved Otsu Multi-Threshold Image Segmentation Method based on Sailfish Optimization

Abstract

Image segmentation is a key step from image processing to image analysis. The classical multi-threshold Otsu algorithm has achieved good results in image segmentation, but it is very time-consuming to use exhaustive search methods to find the optimal threshold. To solve this problem, this paper proposes an improved Otsu multi-threshold image segmentation method based on sailfish optimization(SFO). In order to reduce the time complexity of the algorithm, the heuristic search of sailfish biota is simulated to find the optimal threshold of image segmentation. The inter-class variance of multi-threshold is used as the fitness function of SFO, and the fitness value of each iteration is calculated. The final maximum fitness value is the optimal threshold of image segmentation. The experimental results show that the proposed algorithm in this paper not only improves the segmentation quality, but also shortens the optimization time, which demonstrates the correctness and efficiency of the algorithm.