Amit Bhandari's Homepage. Learn C#. Download Drop Down Menu Maker, Encrypt-o-Doc, wallpapers, screensavers, windows registry tweaks and more. Read motivational quotes of the week or view archives.Forensic Face Recognition System using Neural Network and C#. Dissertation.

Disclaimer | Terms & Conditions | Sitemap

C# basics

Synopsis for the dissertation

Review paper

Screenshots of design

Dissertation in Face Recognition using Neural Network

Welcome to the special section of the website describing the dissertation work.

This part of the website will reflect the milestones achieved by me during the dissertation work which is being carried out in Face Recognition using Neural Networks.

The face recognition process in neural network is being implemented in Visual C#.NET in collaboration with Central Forensic Science Labs, Chandigarh, INDIA.

Download the material published by me which includes basics of C# (presentation), review paper. The references for the work till now are as follows:

I. Aleksander and H. Morton, “An Introduction to Neural Computing,” International Thomson Publishing, 1995.
C. Stergiou, and D. Siganos, “Neural Networks,” http://doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html.
D. Patterson, “Artificial Neural Networks”, Printce Hall India, 1996.
V.V. Starovoitov, D. I. Samal, and D.V. Briliuk, “Three Approaches for Face Recognition,” Proceeding of 6th International conference on Pattern Recognition and Image Analysis, Russia, 21-26 (10) 2002, pp. 707-711.
H.A. Rowley, S. Baluja, and T. Kanade, “Human Face Detection in Visual Scenes,” Technical Report, Department of Computer Science, Carnegie Mellon University, Pittsburgh, 1995, CMU-CS-95-158R.
Yi-Qiong Xu, Bi-Cheng Li, Bo Wang, “Face Detection and Recognition using Neural Network and Hidden Markov Models,” IEEE Conference on Neural Network and Signal Processing, 14-17 (12) (2003), vol. 1, pp. 228-231.
S. Palanivel, B.S. Venkatesh, and B. Yegnanarayana, “Real Time Face Authentication System using Autoassociative Neural Network Models,” Speech and Vision Laboratory, Department of Computer Science and Engineering, Indian Institute of Technology, Madras, Chennai.
S. Lawrence, C.L. Giles, A.C. Tsoi, and A.D. Back, “Face Recognition: A Convolutional Neural Network Approach,” IEEE Transactions on Neural Network, 1997, vol. 8, No. 1, pp. 98-113.
S.-H. Lin, S.Y. Kung, and M. Fang, “A Neural Network Approach to Face/Palm Recognition,” Proc. 5th IEEE Wkshp. Neural Networks Signal Processing, Cambridge, MA, 1995, pp. 323-332.
C. Peacock, A. Goode, and A. Brett, “Automatic forensic face recognition from digital images,” Science & Justice, 2004, vol. 44, No. 1, pp. 29-34.
G.L. Foresti, T. Dolso, “An Adaptive High-order Neural Tree for Pattern recognition,” IEEE Transactions on Systems, Man, Cybernetics, 2004, vol. 34, No. 2, pp. 988-996.
W. Skarbek, “Autoassociative Local Neural Networks for Face Recognition”, http://www.bsp.brain.riken.jp/publications/1996/alnn.pdf.
K. Karibasappa, S. Patnaik, “Face Recognition by ANN using Wavelet Transform Coefficients,” IE (I) Journal – CP, May 2004, vol. 85, pp. 17-22.
Bai-Ling Zhang, Haihong Zhang, and Shuzhi Sam Ge, “Face Recognition by Applying Wavelet Subband Representation and Kernel Associative Memory,” IEEE Transactions on Neural Networks, Jan 2004, vol. 15, No. 1, pp. 166-177.
Daniel B. Graham, and Nigel M. Allinson, “Face Recognition: From Theory to Applications,” NATO ASI Series F, Computer and System Sciences, 1998, vol. 63, pp. 446-456.
A.S. Georghiades, P.N. Belhumeur, and D.J. Kriegman, “From Few to Many: Illustration Cone Models for Face Recognition under Variable Lighting and Pose,” IEEE Trans. Pattern Anal. Mach. Intelligence, 2001, vol. 23, No. 6, pp. 643-660.
T. Sim, S. Baker, and M. Bsat, “The CMU Pose, Illumination, and Expression (PIE) Database of Human Faces,” Technical Report, The Robotics Institute, Carnegie Mellon University, Pittsburgh, CMU-R1-TR-01-02.
T. Sim, S.Baker, and M. Bsat, “The CMU pose, illumination, and expression (PIE) database,” Proceedings of 5th IEEE International Conference on Face and Gesture Recognition, 2002.

The Abstract for the dissertation is as follows:

Human face recognition has become a potential method of biometric authentication, now-a-days, because of its non-intrusive and user-friendly nature. However, it is a challenging problem due to:

Inherent variability of face caused due to age, gender and race.
Different facial expressions and orientations for same person’s face.
Images containing faces have a high degree of variability in size, texture, background and illumination.

Also, face recognition is complex form of pattern recognition. It consists of classifying highly ambiguous input images, with multiple dimensions and matching them with the known ‘images’. Various supervised and unsupervised methods have been proposed to solve the problem. The present thesis intends to study the performance of neural network based approaches for face recognition. The input to the face recognition approach used will be an image pre-processed using various convolutional algorithms for more accurate results.