Comparative analysis of PCA and LDA

Face recognition is one of the most successful applications of image analysis and understanding and has gained much attention in recent years. This paper presents comparative analysis of two most popular appearance-based face recognition methods PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis). It is generally believed that algorithms based on LDA are superior to those based on PCA. In this paper we show that this is not always the case. Our conclusion is that when the training data set is small, PCA can outperform LDA and, also, that PCA is less sensitive to different training data sets.