An Evaluation on Performance of Pca in Face Recognition With Expression Variations

Abstract

Appearance-based recognition methods often encounter difficulties when the input images contain facial expression variations such as laughing, crying or wide mouth opening. In these cases, holistic methods give better performance than appearance-based methods. This paper presents some evaluation on face recognition under variation of facial expression using the combination of PCA and classification algorithms. The experimental results showed that the best accuracy can be obtained with very few eigenvectors and KNN algorithm (with k=1) performs better than SVM in most test cases.