Access control using pca-based face recognition

Access control using pca-based face recognition

Abstract:

This paper will give an approach of face recognition in access control, which can be effectively used in banks, offices, airports, etc. We will be building a simple access control which will make use of the personal computer to perform the face recognition and take appropriate steps depending upon the face recognition results like on mismatch it will sound an alarm and on match found it will grant access to the individual.

One method of identifying faces is to measure the similarity between faces. This is accomplished by using measures such as L1 norm, L2 norm, covariance and correlation. These similarities measures can be calculated on the faces in their original space or on the faces projected into a new space. We present an approach to the detection and identification of human faces and describe working, near-real time face recognition system which tracks a subject’s head and then recognizes by comparing characteristics of the face to those of know individuals.

The most common and least complex method in which these similarity can be calculated, is the subspace created by the eigenvector of covariance matrix of the training data. Our approach treats face recognition as a 2-dimensional recognition problem taking advantage of the fact that faces are normally upright and thus may be described by a set of 2-D characteristic views. Face images are projected onto a feature space (face space) that best encodes the variation among known face images. The face space is defined by the “eigenfaces”, which are the Eigen vectors of the set of faces; they not necessarily correspond to isolated features such as eyes, ears and noses. This is also called as Principal Component Analysis.

for more info visit.
http://www.enjineer.com/forum