摘要
常规的PCA和SVM联合人脸识别算法性能不佳,提出了一种改进的双曲正切函数PSO算法对参数寻优,同时联合PCA和SVM进行人脸识别的算法.该算法采用改进的双曲正切函数PSO算法来进行参数寻优,加快了算法的收敛速度,提高了人脸识别的准确率.该算法用Matlab仿真验证,结果表明它的性能对比常规PCA和SVM联合的人脸识别算法,有明显的优势.
To resolve the problem of the traditional face recognition algorithm based on PCA and SVM, in this paper, a novel method based on an improved hyperbolic tangent function for PSO algorithm combined with PCA and SVM algorithm is introduced, it uses the hyperbolic tangent function for PSO algorithm to optimize SVM parameters, the convergence speed of the algorithm is speeded up, and the face recognition rate is improved. The algorithm is validated on Matlab software, and the results show that it has obvious advantages over traditional PCA and SVM face recognition algorithm.
作者
林志谋
Lin Zhimou(Xiamen Ocean Valional College)
出处
《哈尔滨师范大学自然科学学报》
CAS
2020年第4期51-55,共5页
Natural Science Journal of Harbin Normal University