Principal component analysis based cascade neural network for face recognition

A face recognition system which combines the powerful feature extraction property of principal component analysis (PCA) and classification capability of cascaded neural network is proposed in this paper. For a given data base the features are extracted using PCA. The feature set is divided into training and testing data. The training data is used to train a cascade neural network (CASNN). Testing data are used for performance of the system. This paper uses UMIST face data base. The performance is compared with more popular feed forward neural network (FFNN). The results obtained prove the efficacy of the proposed cascade Neural Network based classifier as compared to the Feed forward neural network classifier.

[1]  Khashayar Khorasani,et al.  Facial expression recognition using constructive feedforward neural networks , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[2]  Martin A. Fischler,et al.  The Representation and Matching of Pictorial Structures , 1973, IEEE Transactions on Computers.

[3]  Adnan Khashman,et al.  A Modified Backpropagation Learning Algorithm With Added Emotional Coefficients , 2008, IEEE Transactions on Neural Networks.

[4]  Francis Galton,et al.  Personal Identification and Description , 2022, Nature.

[5]  Rudy Setiono,et al.  Use of a quasi-Newton method in a feedforward neural network construction algorithm , 1995, IEEE Trans. Neural Networks.

[6]  Guan-Chun Luh,et al.  PCA based immune networks for human face recognition , 2011, Appl. Soft Comput..

[7]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[8]  Timur Ash,et al.  Dynamic node creation in backpropagation networks , 1989 .

[9]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[10]  Vijayan K. Asari,et al.  Gabor Wavelet Based Modular PCA Approach for Expression and Illumination Invariant Face Recognition , 2006, 35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06).

[11]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[12]  P. N. Bellhumer.  Eigenfaces vs. fisherfaces : Recognition using class specific linear projection , 1997 .

[13]  Rama Chellappa,et al.  Background learning for robust face recognition with PCA in the presence of clutter , 2005, IEEE Transactions on Image Processing.

[14]  Ingemar J. Cox,et al.  Feature-based face recognition using mixture-distance , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Yves Chauvin,et al.  A Back-Propagation Algorithm with Optimal Use of Hidden Units , 1988, NIPS.

[16]  Rama Chellappa,et al.  Human and machine recognition of faces: a survey , 1995, Proc. IEEE.

[17]  Lawrence Sirovich,et al.  Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces , 1990, IEEE Trans. Pattern Anal. Mach. Intell..