基于改进麻雀搜索算法的最大指数熵分割方法

为了解决基本麻雀搜索算法(sparrow search algorithm，SSA) 依赖初始种群和求解精度不高的问题，提出一种基于Circle混沌映射和随机游走的改进的麻雀优化算法(improved sparrow optimization algorithm，CRSSA) 。该算法为了增强麻雀种群的多样性,在麻雀初始阶段引入混沌Circle 映射; 采用随机游走对最优麻雀进行扰动，使其在麻雀寻优后期,增强算法全局搜索能力,跳出局部最优。同时选取15个测试函数对其算法进行性能测试。结果表明：与原始的SSA 、蜉蝣算法(mayfly algorithm,MA) 、粒子群优化算法(particle swarm optimization algorithm，PSO) 、鲸鱼优化算法(whale optimization algorithm，WOA) 和灰狼优化算法(gray wolf optimization algorithm，GWO) 相比，改进的麻雀搜索算法具有寻优速度快、求解准确度高和鲁棒性强等优点。将该方法应用在多阈值图像分割中，通过对比不同算法的峰值信噪比(peak-to-signal ratio，PSNR)、结构相似性(structural similarity index，SSIM)、适应度函数值和运行时间性能指标，可有效解决多阈值分割问题，具有一定的工程应用价值。

Maximum Exponential Entropy Segmentation Method Based on Improved Sparrow Search Algorithm

In order to solve the problem that the basic sparrow searchoptimization algorithm (SSA) depends on the initial population and the solution accuracy is not high, an improved sparrow optimization algorithm (CRSSA) based on Circle chaotic mapping and random walk is proposed. In order to enhance the diversity of sparrow population, the algorithm introduces the chaotic Circle mapping in the initial stage of sparrow; the optimal sparrow is perturbed by random walk, which enhances the global search ability of the algorithm and jumps out of the local optimum in the late stage of sparrow search. The results show that the improved sparrow search algorithm is faster, more accurate and more robust than the original sparrow search algorithm (SSA), mayfly algorithm (MA), particle swarm optimization algorithm (PSO), whale optimization algorithm (WOA) and gray wolf optimization algorithm (GWO). Applying this method to multi-threshold image segmentation, it can effectively solve the multi-threshold segmentation problem by comparing the peak-to-signal ratio (PSNR), structural similarity index (SSIM), fitness function values and running time performance indexes of different algorithms, which has certain engineering application value.