Abstract
Linear discriminant analysis (LDA) is a simple but widely used algorithm in the area of face recognition. However, it has some shortcomings in which the relationship of each face to a class is assumed to be crisp. This algorithm was modified by incorporating the membership grade of each face pattern into the calculation of the between-class and within-class scatter matrices, which is known as Fuzzy Fisherface. The Fuzzy Fisherface method introduces a gradual level of assignment of each face pattern to a class by using a membership grading based upon the k-Nearest Neighbor (KNN) algorithm, and it obtains an obviously better performance than the LDA method. However, when computing the fuzzy memberships, only the belong-to information is considered while the not-belong-to information is ignored. In this paper, a further modified fuzzy linear discriminant analysis method is proposed to solve this problem. The experiments were performed on the ORL and FERET face databases, and the results show consistent improvement in the recognition rate.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Kresimir, D., Mislav, G., Sonja, G.: Independent Comparative Study of PCA, ICA, and LDA on the FERET. Data Set. 15, 252–260 (2005)
Gottumukkal, R., Asari, V.K.: An improved face recognition technique based on modular PCA approach. Pattern Recognition Letters 25, 429–436 (2004)
Amar, K., Syed, F.A.: A genetically modified fuzzy linear discriminant analysis for face recognition. Journal of the Franklin Institue 348(10), 2701–2717 (2011)
Jayadeva, R.K., Chandra, S.: Learning the optimal kernel for Fisher discriminant analysis via second order cone programming. European Journal of Operational Research 203(3), 692–697 (2010)
Wankou, Y., Hui, Y., Jingyu, Y.: Face recognition using complete fuzzy LDA. In: Proceedings of the 2008 International Conference on Pattern Recognition, pp. 1–4 (2008)
Keun-Chang, K., Witold: Face recognition using a Fuzzy Fisherface Classifier. Pattern Recognition 38(10), 1717–1732 (2005)
Turk, M., Pentland, A.: Eigenfaces for Recognition. Cognitive Neuroscience 3(1), 71–96 (1991)
Peter, N.B., Joao, P.H., David, J.K.: Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(7), 711–719 (1997)
Wendy, S.Y.: Analysis of PCA-based and fisher discriminant-based image recognition algorithms. Computer Science Technical Report CS-00-103 (2000)
Chen, Z.P., Jiang, J.H., Li, Y.: Fuzzy linear discriminant analysis for chemical data sets. Chemometrics and Intelligent Laboratory Systems 45, 295–302 (1999)
Keller, J.M., Gray, M.R.: A Fuzzy K Nearest Neighbor Classifier Algorithm. IEEE Transactions on Systems, Man and Cybernetics 15(4), 580–585 (1985)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xu, Q., Lu, X., Zeng, W. (2012). Face Recognition Using a Modified Fuzzy Linear Discriminant Analysis Method. In: Lei, J., Wang, F.L., Deng, H., Miao, D. (eds) Artificial Intelligence and Computational Intelligence. AICI 2012. Lecture Notes in Computer Science(), vol 7530. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33478-8_51
Download citation
DOI: https://doi.org/10.1007/978-3-642-33478-8_51
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33477-1
Online ISBN: 978-3-642-33478-8
eBook Packages: Computer ScienceComputer Science (R0)