I. Introduction
Principal component analysis (PCA) is one of the most powerful method used in image processing and pattern recognition applications to perform a specific task such as dimensionality reduction, image compression, and especially face recognition [1], [2]. The PCA method consists of two main steps-(I) computing covariance matrix and (II) extracting eigenvector and eigenvalue. In the first step, the covariance matrix is calculated from the data zero mean which is computed by the subtraction between input data and mean. In the second step, a set of eigenvectors and eigenvalues are extracted by using the covariance matrix based on linear transformation. The eigenvectors are sorted in descending order with respect to their corresponding eigenvalues. In case of face recognition, the eigenvectors selected from 1st to order are used to create the eigenface feature using the projection technique.