《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (6): 1743-1749.DOI: 10.11772/j.issn.1001-9081.2022060945

• CCF第37届中国计算机应用大会 (CCF NCCA 2022) • 上一篇    下一篇

基于改进粒子群优化算法和遗传变异的图像分割模型

梁军, 洪泽泓, 余松森()   

  1. 华南师范大学 软件学院,广东 佛山 528225
  • 收稿日期:2022-06-29 修回日期:2022-08-29 接受日期:2022-09-01 发布日期:2022-09-22 出版日期:2023-06-10
  • 通讯作者: 余松森
  • 作者简介:梁军(1983—),男,江西高安人,讲师,博士,CCF会员,主要研究方向:图论、机器学习、算法设计
    洪泽泓(1997—),男,福建泉州人,硕士研究生,CCF会员,主要研究方向:深度学习、图像分割
    余松森(1972—),男,江西丰城人,教授,博士,CCF会员,主要研究方向:图像处理、智能算法与模型、大数据挖掘分析Email:yusongsen@m.scnu.edu.cn
  • 基金资助:
    广东省基础与应用基础研究基金资助项目(2022A1515140110);广东省基础与应用基础研究基金区域联合基金资助项目(重点项目)(2020B1515120089);广东省普通高校特色创新项目(2019KTSCX035)

Image segmentation model based on improved particle swarm optimization algorithm and genetic mutation

Jun LIANG, Zehong HONG, Songsen YU()   

  1. School of Software,South China Normal University,Foshan Guangdong 528225,China
  • Received:2022-06-29 Revised:2022-08-29 Accepted:2022-09-01 Online:2022-09-22 Published:2023-06-10
  • Contact: Songsen YU
  • About author:LIANG Jun, born in 1983, Ph. D., lecturer. His research interests include graph theory, machine learning, algorithm design.
    HONG Zehong, born in 1997, M. S. candidate. His research interests include deep learning, image segmentation.
  • Supported by:
    Guangdong Basic and Applied Basic Research Foundation(2022A1515140110);Regional Joint Fund for Basic and Applied Basic Research Fund of Guangdong Province (Key Project)(2020B1515120089);Special Innovation Project of Guangdong General Universities(2019KTSCX035)

摘要:

图像分割是由图像处理到图像分析的关键步骤。针对聚类分割对初始聚类中心有较大依赖的局限性,提出了一种基于改进粒子群优化(PSO)算法和遗传变异的图像分割模型PSOM-K(Particle Swarm Optimization Mutations-K-means)。首先,对PSO公式进行改进,即增加了随机邻居粒子位置对自身位置的影响,并扩大了算法的搜索空间,使算法能快速地找到全局最优解;其次,结合遗传算法的变异操作来提高模型的泛化能力;然后,将改进后的PSO算法从红(R)、绿(G)、蓝(B)三通道来初始化k均值(k-means)聚类中心的位置;最后,用k-means从R、G、B三通道对图像进行分割并合并这三通道的图像。在伯克利分割数据集(BSDS500)上的实验结果表明,在k=4时,PSOM-K在特征相似性(FSIM)上相较于CEFO (Chaotic Electromagnetic Field Optimization)算法提升了7.7%~12.69%,相较于WOA-DE(Whale Optimization Algorithm-Differential Evolution)方法提升了5.05%~19.02%。在k=40时,相较于细粒度分割算法HWOA,PSOM-K在FSIM指标最多下降0.45%,但峰值信噪比(PSNR)指标提升7.59%~13.58%。因此,独立3个通道、增加粒子群中随机邻居粒子的位置影响和遗传变异是寻找k-means聚类中心的较优位置的3个有效策略,它们能极大地提高图像分割的性能。

关键词: 图像分割, 粒子群优化算法, 遗传算法, 特征相似性, k均值

Abstract:

Image segmentation is a key step from image processing to image analysis. For the limitation that cluster partitioning has a large dependence on the initial cluster center, an image segmentation model PSOM-K (Particle Swarm Optimization Mutations-K-means) based on improved Particle Swarm Optimization (PSO) algorithm and genetic mutation was proposed. Firstly, the PSO formula was improved by increasing the influence of random neighbor particle positions on its own position, and expanding the search space of the algorithm, so that the algorithm was able to find out the global optimal solution quickly. Secondly, mutation operation of genetic algorithm was combined to improve the generalization ability of the model. Thirdly, the positions of the k-means cluster centers were initialized with the improved PSO algorithm from the three channels: Red (R), Green (G) and Blue (B). Finally, k-means was used to perform the image segmentation from the three channels: R, G, and B, and the images of the three channels were merged. Experimental results on Berkeley Segmentation Dataset (BSDS500) show that the improvement of Feature Similarity Index Measure (FSIM) at k=4 is 7.7% to 12.69% compared to CEFO (Chaotic Electromagnetic Field Optimization) method and 5.05% to 19.02% compared to WOA-DE (Whale Optimization Algorithm-Differential Evolution) method.Compared with the fine-grained segmentation algorithm HWOA (Hybrid Whale Optimization Algorithm), PSOM-K decreases at most 0.45% in FSIM but improves 7.59% to 13.58% in Peak Signal-to-Noise Ratio (PSNR) at k=40. Therefore, three independent channels, increasing the position influence of random neighbor particles in the particle swarm and genetic mutation are three effective strategies to find the better positions of k-means cluster centers, and they can improve the performance of image segmentation greatly.

Key words: image segmentation, Particle Swarm Optimization (PSO) algorithm, genetic algorithm, Feature Similarity Index Measure (FSIM), k-means

中图分类号: