Statistics in face recognition: analyzing probability distributions of PCA, ICA and LDA performance results

In this paper we address the issue of evaluating face recognition algorithms using descriptive statistical tools. By using permutation methodology in a Monte Carlo sampling procedure, we investigate recognition rate results probability distributions of some well-known algorithms (namely, PCA, ICA and LDA). With a lot of contradictory literature on comparisons of those algorithms, we believe that this kind of independent study is important and serves to better understanding of each algorithm. We show how simplistic approach to comparing these algorithms can be misleading and propose a full statistical methodology to be used in future reports. By reporting detailed descriptive statistical results, this paper is the only available detailed report on PCA, ICA and LDA comparative performance currently available in literature. Our experiments show that the exact choice of images to be in a gallery or in a probe set has great effect on recognition results and this fact further emphasizes the importance of reporting detailed results. We hope that this study helps to advance the state of experiment design in computer vision.