An improved grid search algorithm and its application in PCA and SVM based face recognition

In this article, we propose an effective grid search method and apply it in the PCA and SVM based face recognition. Firstly, image preprocessing is employed to reduce the information of face images meanwhile enhance their distinctive features; Secondly, we extract features with PCA algorithm and then deliver the dimension reduced data to SVM for classification. During the process of building SVM classifier, our improved multi-parameter grid search algorithm is adopted to advance the accuracy and spatiotemporal efficiency of its parameter optimization. Experiments show the high efficiency and better recognition rate of our method. © 2014 Binary Information Press.