摘要
针对传统多级阈值图像分割方法精度低、收敛速度慢的问题,提出一种改进的沙猫群优化算法(Improved Sand Cat Swarm Optimization, ISCSO)用于全局优化,并应用于2D-OTSU多阈值图像分割任务。通过使用Henon混沌映射和反向折射机制初始化种群,使得种群的分布更加均匀,提高搜索的起始状态,从而增加算法的全局搜索能力;采用非线性灵敏度更新公式来平衡搜索多样性和收敛精度;引入可变螺旋搜索策略改进位置更新算法,以确保算法具有较好的搜索多样性和跳出局部最优解的能力。选取6张测试图像对ISCSO算法进行2DOTSU多阈值图像分割实验,采用峰值信噪比(PSNR)、特征相似性指数(FSIM)和结构相似性指数(SSIM)对实验结果进行评价。实验结果表明,基于ISCSO算法的2D-OSTU多阈值图像分割方法在图像分割任务中85.2%的结果优于对比算法,具有较强的搜索精度和收敛速度,这证明了ISCSO算法在图像分割领域的有效性和潜力。
Aiming at the problems of low accuracy and slow convergence of traditional multilevel threshold image segmentation methods,an improved sand cat swarm optimization(ISCSO)algorithm was proposed for global optimization and applied to 2D-OTSU multi-threshold image segmentation task.By using Henon chaotic mapping and inverse refraction mechanism to initialize the population,the distribution of the population was made more uniform,and the starting state of the search was improved,so as to increase the global search capability of the algorithm;the nonlinear sensitivity update formula was adopted to balance the search diversity and convergence accuracy;the variable spiral search strategy was introduced to improve the position update algorithm,so as to ensure that the algorithm has better search diversity and the ability to jump out of the local optimal solution.The algorithm has the ability of searching diversity and jumping out of local optimal solutions.Six test images were selected for the 2D-OTSU multi-threshold image segmentation experiments of ISCSO algorithm,and the peak signal-to-noise ratio(PSNR),feature similarity index(FSIM)and structural similarity index(SSIM)were used to evaluate the experimental results.And the experimental results show that,the result of 85.2%obtained by using the 2D-OTSU multi-threshold image segmentation based on the ISCSO algorithm is better than the comparison algorithm. And the method has strong search accuracy and convergence speed.This proves the effectiveness and potential of ISCSO algorithm in the field of image segmentation.
作者
陈昳
潘广贞
CHEN Die;PAN Guangzhen(School of Software,North University of China,Taiyuan 030051,China)
出处
《中北大学学报（自然科学版）》
CAS
2024年第4期411-419,共9页
Journal of North University of China(Natural Science Edition)
关键词
沙猫群优化算法
多阈值图像分割
2D-OTSU
群智能优化算法
sand cat swarm optimization algorithm
multi-threshold image segmentation
2D-OTSU
swarm intelligence optimization algorithm
