Browse > Article
http://dx.doi.org/10.5391/JKIIS.2005.15.4.400

A Face Recognition System using Eigenfaces: Performance Analysis  

Kim, Young-Lae (강릉대학교 전자공학과)
Wang, Bo-Hyeun (강릉대학교 전자공학과)
Publication Information
Journal of the Korean Institute of Intelligent Systems / v.15, no.4, 2005 , pp. 400-405 More about this Journal
Abstract
This paper analyzes the performance of a face recognition algorithm using the eigenfaces method. In the absence of robust personal recognition schemes, a biometric recognition system has essentially researched to improve their shortcomings. A face recognition system in biometries is widely researched in the field of computer vision and pattern recognition, since it is possible to comprehend intuitively our faces. The proposed system projects facial images onto a feature space that effectively expresses the significant variations among known facial images. The significant features are known as 'eigenfaces', because they are the eigenvectors(principal components) of the set of faces. The projection operation characterizes an individual face by a weighted sum of the eigenface features, and to recognize a particular face it is necessary only to compare these weights to those of known individuals. In order to analyze the performance of the system, we develop a face recognition system by using Harvard database in Harvard Robotics Laboratory. We present the recognition rate according to variations on the lighting condition, numbers of the employed eigenfaces, and existence of a pre-processing step. Finally, we construct a rejection curve in order to investigate the practicability of the recognition method using the eigenfaces.
Keywords
얼굴인식;고유얼굴;전처리;히스토그램 평활화;조명;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Thomas Heseltine, Nick Pears and Jim Austin, 'Evaluation of image pre-processing techniques for eigenface based face recognition,' The Preceedings of the Second International Conference on Image and Graphics, SPIE, vol. 4875, pp. 677-685, 2002
2 R. Brunelli and T. Poggio, 'Face Recognition: Features versus Templates,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 10, pp. 1,042-1,053, Oct. 1993   DOI   ScienceOn
3 A. Samal and P. Iyengar, 'Automatic Recognition and Analysis of Human Faces and Facial Expressions: A Survey,' Pattern Recognition, vol. 25, pp. 65-77, 1992   DOI   ScienceOn
4 Harvard Database, http://cvc.yale.edu
5 T. Kanade, Computer Recognition of Human Faces, Basel and Stuttgart: Birkhauser, 1997
6 M. Turk and A. Pentland, 'Face Recognition Using Eigenfaces,' Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 586-591, 1991
7 Peter N. Belhumeur, J. P. Hespanha, D. J. Kriegman, 'Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, No.7, July 1997
8 A. K. Jain, A. Ross, S. Prabhakar, 'An Introduction to Biometric Recognition,' IEEE Transactions on Circuits and Systems for Video Technology, vol. 14, No. 1, January 2004
9 M. Kirby and L. Sirovich, 'Application of the Karhenen-Loéve Procedure for the characterization of human faces,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, 1990
10 M. Turk and A. Pentland, 'Eigenfaces for Recognition,' J. Cognitive Neuroscience, vol. 3, no. 1, 1991