Parameter Optimization Based on Quantum Genetic Algorithm for Generalized Fuzzy Entropy Thresholding Segmentation Method

Abstract

Generalized fuzzy entropy thresholding method segments the image based on the principle that the membership degree of the threshold point is equal to m (0< m <1), which can obtain better segmentation result than that of traditional fuzzy entropy method, especially for images with bad illumination. The key step of this method is how to determine the parameter m effectively. In this paper, we use quantum genetic algorithm to solve it. Quantum genetic algorithm is used to automatically determine the optimal parameter m and the membership function parameters (a,b,c) respectively based on an image segmentation quality evaluation criterion and the maximum fuzzy entropy criterion, realizing the automatic selection of the threshold in generalized fuzzy entropy-based image segmentation method. Experiment results show that our method can obtain better segmentation results than that of traditional fuzzy entropy-based method.