基于LWSFLA-SVM的人脸识别算法*

目的用线性调整惯性权重的蛙跳算法(linear decreasing inertia weight shuffled frog leaping algorithm,LWSFLA)训练支持向量机(support vectors machines,SVM),解决人脸识别中SVM在训练样本数较多且维数较高时,识别效果不理想的缺陷。方法该算法先用反向学习法产生初始群体提高初始解的质量,再修改最差青蛙的更新策略,并引入线性递减的惯性权重,最后应用于人脸识别中。结果与结论 ORL和CAS-PEAL-R1人脸库的仿真实验表明,LWSFLA-SVM方法的人脸识别时间短,识别率高,在训练样本不足时,识别效果良好。

Face recognition algorithm based on LWSFLA-SVM

Purposes—To solve the defects of the undesirable recognition result in face recognition by using the linear adjusting inertia weight shuffled frog leaping algorithm (LWSFLA ) to train the support vectors machines (SVM) when there are a large number of training samples and higher dimen‐sion of training samples for the SVM .Methods—In this algorithm ,the quality of the initial solution was firstly improved by the initial population which is produced with the inverse learning method . Then ,the update strategy for the worst frog was modified and the linear decreasing inertia weight was introduced .Finally ,the LWSFLA is applied to the face recognition .Results and Conclusions—The simulation results of experiments on the ORL and CAS‐PEAL‐R1 face database show that the LWS‐FLA‐SVM method boasts short time and high recognition rate ,and the recognition effect of LWS‐FLA‐SVM is good when the training samples are insufficient .