Author : Ms. Sarika Ashok Sovitkar 1
Date of Publication :7th February 2017
Abstract: now a day as lots of research was done in computer vision and image processing from last few decades. It is possible to develop a system for automated attendance using face recognition technique. In this paper we implement the PCA and LDA algorithm for face recognition technique and compare result. We found that in PCA as the number of samples per persons in training dataset does on increase the accuracy also increase for recognition. To store the huge sample dataset is the main drawback of this algorithm and also we found that in real time there are such requirement the will have to recognize a person from only one sample dataset as training dataset. In LDA we extract the components in training phase and compare them with the extracted components of dataset of testing image in testing phase. As we succeed to decrease the number of samples to only two samples for training and the results found are encouraging. The experiments are performed using different variations in lighting, illumination, facial expression, partial occlusion and imprecise localization of face area.
Reference :
-
- W. Zhao, R. Chellappa, A. Rosenfeld, and J. Phillips, “Face Recognition: A Literature Survey”, Technical Report, CFAR-TR00-948, Univ. of Maryland, 2000. (Revised 2002).
- M Turk and A Pentland, “Eigenfaces for recognition”, Journal of Cognitive Neuroscience, Vol. 3, No.1, pp. 71- 86, 1991.
- P. N. Belhumeur, J.P. Hespanha, D.J. Kriegman, “Eigenfaces vs. Fisherfaces: recognition using class specific linear projection”, IEEE Trans. Pattern Anal. Mach. Intell., Vol. 19, No. 7, pp. 711-720, 1997.
- A M Martinez and A. C. Kak, “PCA versus LDA”, IEEE Trans. Pattern Anal. Mach. Intell., Vol. 23, 2001, pp. 228-233, 2001.
- H. Yu and J. Yang, “A direct LDA algorithm for highdimensional data --- with application to face recognition”, Pattern Recognition, Vol. 34, pp. 2067- 2070, 2001.
- P C Yuen, W S Chen and J Huang, “A novel subspace LDA algorithm for face recognition with small number of training images”, Submitted to IEEE Transactions on Circuits and Systems for Video Technology, Special issue on Image- and Video based Biometrics, 2002
- R Huang, Q Liu, H Lu and S Ma, “ Solving small sample size problem in LDA”, Proceeding of International Conference in Pattern Recognition (ICPR 2002), Vol. 3, Aug 2002.
- A M Martinez, ”Recognizing imprecisely localized partially occluded and expression variant faces from a single sample per class”, IEEE Trans. Pattern Anal. Mach. Intell., Vol. 24, N0. 6, pp. 748-763, 2002.
- Jianxin Wu and Zhi-Hua Zhou, “Face Recognition with One Training Image per Person”, Pattern Recognition Letters, vol.23, no.14, pp.1711-1719, 2002.
- L Wiskott, J Fellous, and C von der Malsburg, "Face Recognition by Elastic Bunch Graph Matching", IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 19, pp. 775-779, 1997.
- J Huang, P C Yuen and J H Lai, Combining local and global features for face recognition, Proceedings of ACCV 2002. No. 23-25, 2002.
- S.A. Sovitkar, S.S. Kawthekar, “A Review OnAutomated Attendance Management System Using Face Recognition”, Golden Research Thoughts (GRT), Vol. 5, no. 16, 2016.