摘要
针对传统多阈值图像分割方法效率低、分割精度差,提出基于混沌与对立学习正余弦算法COLSCA的多阈值图像分割方法。为提高正弦余弦算法的寻优精度和收敛速率,引入非线性对数曲线对正余弦振幅转换参数进行更新,平衡算法全局勘探与局部开发能力;利用混沌搜索对种群精英个体进行变异,增强局部开发能力;设计对立学习增强种群多样性,避免局部最优解。将Kapur熵作为适应度函数,利用COLSCA算法求解图像分割阈值。实验结果表明,该算法可以有效提升图像分割精度和分割效率。
Traditional multilevel thresholds image segmentation algorithms have low efficiency and poor segmentation accuracy.Aiming at this problem,a multilevel thresholds image segmentation algorithm was put forward based on improved sine cosine algorithm COLSCA integrating with chaos and opposite learning.To improve the optimizing precision and the convergence speed in sine cosine algorithm,the nonlinear logarithmic curve was used to update sine cosine amplitude transfer parameter for bala-ncing global search and local development capacity.The chaotic search mechanism was used to optimize elite individuals in population and the capacity of local development was enhanced.The opposite learning was introduced to promote the population diversity and avoid the local optimal solution.Kapur entropy was used as fitness function,and COLSCA algorithm was used to search the optimal image segmentation thresholds.It is confirmed that the proposed algorithm can enhance the accuracy of image segmentation and segmentation efficiency.
作者
杨淼
YANG Miao(School of Information Science and Engineering,Wuhan University of Science and Technology,Wuhan 430080,China;Intelligent Manufacturing Institute,Changzhou Vocational Institute of Engineering,Changzhou 213164,China)
出处
《计算机工程与设计》
北大核心
2022年第11期3177-3186,共10页
Computer Engineering and Design
基金
常州工程职业技术学院科研基金项目(11130300119006)
常州大学高等职业教育研究院课题基金项目(CDGZ2021048)
常州市科技计划基金项目(CE20205006)。
关键词
图像分割
正弦余弦算法
混沌搜索
对立学习
多阈值
精英变异
迭代寻优
image segmentation
sine cosine algorithm
chaotic search
opposite learning
multilevel thresholds
elite mutation
iterative optimization
