The impact of segmentation on face recognition using the principal component analysis (PCA)

This paper provides an example of the face recognition using PCA method and impact of segmentation algorithm `Belief Propagation´ on recognition rate. Principle component analysis (PCA) is a multivariate technique that analyzes a face data in which observation are described by several inter-correlated dependent variables. The goal is to extract the important information from the face data, to represent it as a set of new orthogonal variables called principal components. The paper presents a proposed methodology for face recognition based on preprocessing face images using Belief Propagation segmentation algorithm. The algorithm has been tested on 50 subjects (100 images). The proposed method first was tested on ESSEX face database and next on own segmented face database. Test results gave a recognition rate of about 84% for ESSEX database and 90% for our segmented database. The proposed algorithm shows that the segmentation has a positive effect for face recognition and accelerates the recognition PCA technique.