Developing a technique for face recognition using pca.
Loading...
Date
2016
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
UMT.Lahore
Abstract
Face recognition has been an active area of research with numerous applications since late 1980s. In this paper, different approaches for face recognition along with PCA approach are discussed. There are two major categories under which different approaches fall, that are feature based recognition and principal component analysis. Principal component analysis; based on information theory concepts, seek a computational model that best describes a face which is done by extracting the most relevant information contained in the face. Eigen face approach also uses principal component analysis method; in which a small set of characteristic pictures are used to describe the variation among different face images eigen face approach is one of the earliest appearance-based face recognition methods, which was developed by M. Turk and A. Pentland [1] in 1991.
A face recognition system, based on the eigen face approach is proposed with minimization of dimensions. Eigen face approach is an adequate method to be used in face recognition due to its simplicity, speed and learning capability. A number of different scenarios were created to evaluate the performance of proposed algorithm for efficient face recognition. The proposed system attempts to minimization of memory consumption. The results also demonstrate that the proposed algorithm is quite robust to head/face orientation but sensitive to different illumination ratios. At the end of thesis, a couple of ways are also suggested to improve the recognition rate. Experimental results are given to demonstrate the variability of the proposed face recognition method.