Maximum Fuzzy Entropy Image Segmentation Based on Artificial Fish School Algorithm

Abstract

The maximum fuzzy entropy algorithm is one of the effective methods of image segmentation, researchers often combine maximum fuzzy entropy and genetic algorithm (GA), but the algorithms have the defects of complexity encoding and unstable search, etc. To improve the algorithms, artificial fish school algorithm (AFSA) is introduced to more rapid optimization of maximum fuzzy entropy, this paper proposes a novel maximum fuzzy entropy image segmentation algorithm based on AFSA (AFSA-based MFEISA). Firstly, the histogram of the image and the probability of each gray level are counted up, and then the multiple threshold integer coding is designed and the maximum fuzzy entropy is converted to the objective function of coding, finally, the maximum fuzzy entropy and its corresponding thresholds are obtained by the improved AFSA and the image is segmented. The experimental results show that the proposed algorithm can achieve better segmentation effect than OTSU algorithm and maximum entropy algorithms, at the same time, it not only has more simple and effective coding scheme and better segmentation effect than the algorithms based on fuzzy entropy and GA, etc, but also it shows better stability and convergence.