Abstract
In this work, we use the PCA based eigenface method to build a face recognition system that have recognition accuracy more than 97% for the ORL database and 100% for the CMU databases. However, the main goal of this research is to identify the characteristics of eigenface based face recognition while, (1) the number of eigenface features or signatures in the training and test data is varied; (2) the amount of noise in the training and test data is varied; (3) the level of blurriness in the training and test data is varied; (4) the image size in the training and test data is varied; (5) the variations in facial expression, pose and illumination are incorporated in the training and test data; and (6) different databases with different characteristic for example with aligned images and non-aligned images, bright and dark image are used. We have observed that, (1) in general the increase of the number of signatures on images increases the recognition rate, however, the recognition rate saturates after a certain amount of increase; (2) the increase in the number of samples used in the calculation of covariance matrix in the PCA increases the recognition accuracy for a given number of individuals to identify; (3) the increase in noise and blurriness have different affect on the recognition accuracy; (4) the reduction in image-size has very minimal effect on the recognition accuracy; (5) if less number of individuals are supposed to be recognized then the recognition accuracy increases; (6) alignment of the facial images increases recognition accuracy; and (7) expression and pose have minimal effect on the recognition rate while illumination has great impact on the recognition accuracy.
Similar content being viewed by others
References
Chellapa R, Wilson CL, Sirohey S (1995) Human and machine recognition of faces: a survey. In: Proceedings of the IEEE, pp 705–740
Samal A, Lyengar P (1992) Automatic recognition and analysis of human faces and facial expression: a survey. Pattern Recog 25:65–77
Yang MH, Kriegman D, Ahuja N (2002) Detecting faces in images: a survey. IEEE Trans Pattern Anal Mach Intell 34–58
Zhao W, Chellappa R, Phillips PJ, Rosenfeld A (2003) Face recognition: a literature survey. ACM Comput Surv 35:399–458
Kirby M, Sirovich L (1990) Application of the Karhunen–Loeve procedure for the characterization of human faces. IEEE Trans Pattern Anal Mach Intell 12(1):103–108
Turk M, Pentland A (1991) Eigenfaces for recognition. J Cognitive Neurosci 13(1):71–86
Moon H, Phillips PJ (2001) Computational and performance aspects of PCA-based face-recognition algorithms. Perception 30:303–321
Chen S, Shan T, Lovell BC (2007) Robust face recognition in rotated eigenspaces. In: Proceedings of Image and Vision Computing, New Zealand, pp 1–6
Zhang DQA, Zhou ZH, Chen SC (2006) Diagonal principal component analysis for face recognition. Pattern Recogn 39:140–142
Bartlett MS, Movellan JR, Sejnowski TJ (2002) Face recognition by independent component analysis. IEEE Trans Neural Netw 13(6):1450–1464
Lin SH, Kung SY, Lin LJ (1997) Face recognition/detection by probabilistic decision based neural network. IEEE Trans Neural Netw 114–132
Huang J, Blanz V, Heisele B (2002) Face recognition using component-based SVM classification and morphable models In: Lee SW, Verri A (eds) Lecture notes in computer science, vol 2388, Springer, Berlin, pp 334–341
Shan S, Gao W, Zhao D (2003) Face identification based on face-specific subspace. Int J Imag Syst Technol 23–32
Karande KJ, Sanjay N. Talbar (2008) Face recognition under variation of pose and illumination using independent component analysis. ICGST-GVIP, ISSN 1687-398X, 8(IV), December 2008
Zhao W, Chellappa R, Phillips PJ (1999) Subspace linear discriminant analysis for face recognition. Technical Report, CAR-TR-914. Center for Automation Research, University of Maryland, MD
Su H, Feng DD, Zhao R (2002) Face recognition using multi-feature and radial basis function Network. In Proceeding of the Pan-Sydney Area Workshop on Visual Information Processing, Sydney
Delac K, Grgic M, Grgic S (2007) Image compression effects in face recognition systems. In: K Delac, Grgic M (eds) Face Recognition, I-Tech Education and Publishing, Vienna, pp 75–92
Liu C (2002) Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition. IEEE Trans Image Process 11:467–476
Liu C (2004) Gabor-based kernel pca with fractional power polynomial models for face recognition. IEEE Trans Pattern Anal Mach Intell 26:572–581
Liu C, Wechsler H (2003) Independent component analysis of gabor features for face recognition. IEEE Trans Neural Netw 14:919–928
Amin MA, Afzulpurkar NV, Dailey MN, Esichaikul V, Batanov DN (2005) Fuzzy-C-mean determines the principle component pairs to estimate the degree of emotion from facial expressions. In: Proceedings of FSKD, Springer, Berlin, pp 484–493
Dailey MN, Cottrell GW, Padgett C, Adolphs R (2002) EMPATH: a neural network that categorizes facial expressions. J Cogn Neurosci 14:1158–1173
Amin MA, Yan H (2009) An empirical study on the characteristics of gabor representations for face recognition. Int J Pattern Recogn Artif Intell 23:401–431
Liu CC, Liu DQ, Yan H (2007) Local discriminant wavelet oacket coordinates for face recognition. J Machine Learn Res 8:1165–1195
Bachmann T (1991) Identification of spatially quantized tachistoscopic images for faces: how many pixels does it take to carry identify? Eur J Cogn Psychol 3:87–103
Zhang B, Shan S, Chen X (2010) Fusing local patterns of gabor magnitude and phase for face recognition. IEEE Trans Imag Process 19(5):1349–1361
Poon B, Amin MA, Yan H (2009) PCA based face recognition and testing criteria. In: Proceedings of the 2009 international conference on machine learning and cybernetics, pp 2945–2949
Kim K (2003) Face recognition using principle component analysis. Department of Computer Science, University of Maryland, College Park
ORL face database, http://www.cl.cam.ac.uk/researchh/dtg/attarchive/facedatabase.html
CMU face database, http://vasc.ri.cmu.edu/idb/html/face/facial_expression/index.html
Nott face database, http://pics.psych.stir.ac.uk/
JAFFE Database, http://www.kasrl.org/jaffe_download.html
Tarr MJ (2008) Caucasian face database, Face-Place Face Database Project, http://www.face-place.org/
Indian face database (2002) www.cs.umass.edu/~vidit/IndianFaceDatabase
Asian face database from Intelligent Media Laboratory, www.imlab.postech.ac.kr
Essex University Face Database, http://cswww.essex.ac.uk/mv/allfaces/faces94.html
Acknowledgments
This work is supported in part by a grant from City University of Hong Kong (Project 9610034).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Poon, B., Ashraful Amin, M. & Yan, H. Performance evaluation and comparison of PCA Based human face recognition methods for distorted images. Int. J. Mach. Learn. & Cyber. 2, 245–259 (2011). https://doi.org/10.1007/s13042-011-0023-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-011-0023-2