摘要
利用SAR图像的Hu不变矩,仿射不变矩,以及Zernike不变矩,通过调整学习因子后的PSO对SVM进行优化,提出了基于改进PSO-SVM的SAR图像分类识别算法。该方法主要调节PSO的异步学习因子,加强粒子的学习能力,在算法性能上不仅减小粒子陷入局部最优的概率,而且能有效提高算法的收敛性。最后,对SAR图像进行分类识别实验,结果表明:该算法比其他算法识别率显著提高。
Hu invariant moments,Affine invariant moments and Zernike invariant moments of SAR images are used to optimize SVM by adjusting PSO after adjusting learning factors,and then SAR image classification and recognition algorithm based on improved PSO-SVM is proposed. This method mainly regulates the asynchronous learning factor of PSO,and strengthens the learning ability of particles. In terms of algorithm performance,it not only reduces the probability of particles falling into local optimum,but improves the convergence of algorithm effectively. Finally, the SAR image classification experiment is carried out. The results show that the recognition rate of the algorithm is significantly higher than that of other algorithms.
作者
张肖敏
王鹏
白艳萍
ZHANG Xiaomin;WANG Peng;BAI Yanping(School of Science,North University of China,Taiyuan 030051,China)
出处
《重庆理工大学学报(自然科学)》
CAS
北大核心
2018年第8期165-169,共5页
Journal of Chongqing University of Technology:Natural Science
基金
国家自然科学基金资助项目(61774137)
山西省自然科学基金资助项目(201701D22111439
201701D221121)
山西省回国留学人员科研项目(2016-088)