In the last couple of decades, engineers, neuroscientists and psychologists have turned their attention to face recognition by humans and computer vision systems. Images of different complexities have been tested with a variety of methods. The goals of each research vary, as vary the applications. We present a neural method of recognizing faces using features obtained from compression of these faces with different methods. The extracted fea ti tres are used as inputs to a feedforward neural network. The neural network is trained with backpropagation and ALOPEX. Different types of featicre extraction are used and the results of training and testing for recognition based on the above mentioned methods are compared. ALOPEX converges much faster than backpropagation to a global maximum. Testing in both methods is as good as the learning of the network.
Micheli-Tzanakou, E. "Face Recognition in Alzheimer's Disease", INNS, World Congress on Neural Networks, in press, 1995.
2.
Carey, S. "A case study: Face recognition," in Explorations in The Biological Language, E. Walker, Ed. New York: Bradford, 1987, pp. 175-201.
3.
Carey, S., R. Diamond, and B. Woods, "The development of face recognition—A maturational component ?" Develop. Psych. vol.16, pp. 257-269, 1980.
4.
Cheng, Y. , K. Liu, J. Yang, and H. Wang, "A robust algebraic method for human face recognition," in Proc. 11th Int. Conf. on Patt. Recog., 1992, pp. 221-224.
5.
Craw, I., H. Ellis and J. Lishman, "Automatic extraction of face features," Patt. Recog. Lett.,vol. 5, pp. 183-187, 1987.
6.
Craw, I.,D. Tock, and A. Bennett, "Finding face features," in Proc. 2nd Europe. Conf. on Compu. Vision, 1992, pp. 92-96.
7.
Davies, G., H. Ellis, and E.J. Shepherd, Perceiving and Remembering Faces. New York: Academic, 1981.
8.
Ellis, H.D. "Introduction to aspects of face processing: Ten questions in need of answers," in Aspects of Face Processing, H. Ellis, M. Jeeves, F. Newcombe, and A. Young , Eds. Dordrecht: Nijhoff, 1986, pp. 3-13.
9.
Gordon, G. "Face recognition based on depth maps and surface curvature," in SPIE Proc.: Geometric Methods in Computer Vision, vol. 1570, 1991, pp. 234-247.
10.
Haig, N.D. "Investigating face recognition with an image processing computer," in Aspects of Face Processing, H. D. Ellis, M. Jeeves, F. Newcombe, and A Young , Eds. Dordrecht: Nijhoff, 1985, pp. 410-425.
11.
Manjunath, B.S. , R. Chellappa, and C. v. d. Malsburg, "A feature based approach to face recognition," in Proc. IEEE Computer Soc. Conf. on Computer Vision and Patt. Recog., 1992, pp. 373-378.
12.
Laughery, K.R. , J.B.T. Rhodes, and J.G.W. Batten, "Computer-guided recognition and retrieval of facial images," in Perceiving and Remembering Faces, G. Davis, H. Ellis, and J. Shepherd, Eds. New York: Academic, 1981, pp. 250-269.
13.
Hay, D.C. and A.W. Young, "The human face", in Normality and Pathology in Cognitive Function , A. W. Ellis, Ed. London: Academic, 1982, pp. 173-202.
14.
Hong, Z. "Algebraic feature extraction of image for recognition," Patt. Recog., vol. 24, pp. 211-219,1991.
15.
Brunelli, R. and T. Poggio, "HyperBF networks for gender classification," in Proc. DARPA Image Understanding Workshop, 1992, pp. 311-314.
16.
Golomb. B.A. and T.J. Sejnowski, "SEXNET: A neural network identifies sex from human faces," in Advances in Neural Information Processing Systems 3, D.S. Touretzky and R. Lippmann , Eds. San Mateo, CA: Morgan Kaufmann, 1991, pp. 572-577.
17.
Kohonen, T., Sclf Organization and Associative Memory. Berlin : Springer, 1988.
18.
Jain, A.K., Fundamentals of Digital Image Processing. Englewood Cliffs, NJ:Prentice Hall, 1989.
19.
Wintz, P.A. , "Transform picture coding," Proc. IEEE, vol. 60, pp. 809-820, 1972.
20.
Kirby, M. and L. Sirovich, "Application of the Karhunen-Loeve procedure for the characterization of human faces," IEEE Trans. Patt. Anal. and Mach. Intell. , vol. 12. pp. 103-108, 1990.
Turk, M.A., and A.P. Pentland, "Face recognition using eigenfaces," inProc. Int. Conf. on Patt. Recog., 1991, pp. 586-591.
23.
Ellis, H., M. Jeeves, F. Newcombe, and A. Young, Aspects of Face Processing. Dordrecht: Nijhoff, 1986.
24.
Ellis, H. " The role of the right hemisphere in face perception" in Function of the Right Cerebral Hemisphere, A. W. Young , Ed. London, Academic, 1983, pp. 33-64.
25.
Rahardja, A. , A. Sowmya, and W. Wilson, "A neural network approach to component versus holistic recognition of facial expressions in images," in SPIE Proc.: Intell. Robots and Computer Vision X: Algorithm and Techn ., vol.1607,1991, pp. 62-70.
26.
Perret, D.L. , A.J. Mistlin, and A.J. Chitty, "Visual neurons responsive to faces," Trends in Neuroscience, vol. 10, pp. 358-363, 1987.
27.
Perret, D.I. , A.J. Mistlin, A.J. Chitty, P.A. Smith, D.D. Potter, R. Broennimann, and M.H. Arries, "Specialized face processing and hemispheric asymmetry in man and monkey: Evidence from single unit and reaction time studies, Beliav. Brain Res. , vol. 29, pp. 245-258, 1988.
28.
Perret, D.I. , P.A. Smith, D.D. Potter, A.J. Mistlin, A.S. Head, A.D. Milner, and M.A. Jeeves, "Visual cells in temporal cortex sensitive to face view and gaze direction," in Proc. Royal Soc. of London , Series B, 1985, vol. 223, pp. 293-317.
29.
Micheli-Tzanako, E. and G.M. Binge " F-CORE: A Fourier based Image Compression and Reconstruction Technique " SPIE Proc. on Visual Comm. and Image Processing IV, vol: 1199, 1563-1574,1989.
Hu, M.K. "Visual Pattern Recognition by Moment Invariants ," IEEE Trans. on Inform. Theory, 8179-187, 1962.
32.
Grossman, A. and J. Morlet.Decomposition of Hardy functions into square integralwaviest of constant shape. SIAM I.Matli , 15:723-736,1984.
33.
Strang, G.T.Wavelets and dilation techniques: A brief introduction . SIAM Rev, 31:4:614-627, 1989.
34.
Mallat, S.G. "A theory for multiresolution signal decomposition: The wavelet representation ." IEEE Trans. PAMI, 11:7:674-693, July 1989.
35.
Daubechies, I. "The wavelet transform, time-frequency localization and signal analysis." IEEE Info.Theory, 6:5:961-1005, September 1990.
36.
Burt, P.J. and E.H. Adelson. "The Laplacian pyramid as a compact image code." IEEE Trans. Communication, 31:532-540, April 1983.
37.
Lippmann, R.An Introduction to Computing With Neural Nets . IEEE ASSP Magazine : 4-22, April 1987.
38.
Kohonen, T.An Introduction to Neural Computing. Neural Networks1: 3-16, 1988.
39.
Hecht-Nielson, R. "Neurocomputing: Picking the Human Brain." IEEE Spectrum, pp. 36-41, March, 1988.
40.
Anderson, J.A. and E. Rosenfeld.Neurocomputing: Foundations of Research . MIT Press: Cambridge, MA, 1988.
41.
Tou, J.T. and R.C. Gonzalez. "Automatic Recognition of Handwritten Characters via Feature Extraction and Multilevel Decision." Int. J. Comp. Inf. Sci.1: 43-65, 1972.
42.
Tou, J.T. and R.C. Gonzalez.Pattern Recognition Principles. Addison-Wesley Publishing Co.: Reading, Ma., pp. 243-246,1974.
43.
Minsky, M. and S. Papert. "Perceptrons: An Introduction to Computational Geometry ," M.LT. Press, 1969.
44.
Huang, S. and Huang, Y. "Bounds on the Number of Hidden Neurons in Multilayer Perceptrons." IEEE Trans. on Neural Networks. vol.2, no.1, pp. 47-55, Jan.1991.
45.
Kung, S.Y., Hwang, J. and Sun, S. "Efficient modeling for multilayer feedforward neural nets." Proc. IEEE Conf. on Acoustics, Speech Signal Processing, New York, pp. 2160-2163, April 1988.
46.
Mirchandani, G. "On Hidden Nodes for Neural Nets." IEEE Trans. on Circuits and Systems. 36(5) 661-664, 1989.
47.
Moore, K. "Artificial Neural Networks: Weighing the different ways to systemizethinking ." IEEE Potentials, pp. 23-28, Feb.1992.
48.
McCulloch, W.C. and Pitts, W. "A logical calculus of the ideas immanent in nervous activity." Bulletin of Mathematical Biophysics.5: 115-133, 1943.
49.
Hebb, D.The Organization of Behavior. Wiley, New York, NY, 1949.
50.
Rosenblatt, F.T"he Perceptron: A probabilistic model for information storage andorganization in the brain." Psychological Review65: 386-408, 1958.
51.
Rosenblatt, F.Principle of Neurodynamics, Spartan Books, New York, 1959.
52.
Rosenblatt, F.Principles of Perceptrocts, Spartan Press, Washington, D.C., 1962.
53.
Widrow, B. and Lehr, M.A. "30 Years of Adaptive Neural Networks: Perceptron, Madaline, and Backpropagation ." Proc. IEEE, vol. 78, no. 9, 1415-1442, Sept. 1990.
54.
Werbos, P.J.Beyond Regression: New Tools for Prediction aud Analysis in the Behavioral Sciences. Ph.D. Thesis, Harvard University, Cambridge, MA. 1974.
55.
Parker, D.B.Learning Logic. Technical Report. Center for Computational Research in Economics and Management Science, M.I.T. Cambridge, MA. 1985.
56.
Rumelhart, Hinton, and Williams. " Learning Internal Representations by Error Propagation", in Rumelhart and McClelland (eds.), Parallel Distributed Processing: vol. 1: Foundations . MIT Press, 1986.
57.
Tzanakou, E. and Harth, E. "Determination of Visual Receptive Fields by Stochastic Methods." Biophysics Journal, 15:(42a), 1973.
58.
Tzanakou, E. , Michalak, R., & Harth, E. "The ALOPEX process: visual receptive fieldsby response feedback." Biol. Cyberrl.35, 161-174, 1979.
59.
Ciaccio, E. and Tzanakou, E. "The ALOPEX process: Application to real-time reduction of motion artifact." Annual Int. Cotif. of IEEE EMBS vol. 12, no. 3, pp. 1417-1418,1990.
60.
Dasey, T.J. , and Micheli-Tzanakou , E. "A pattern recognition application of the Alopex process with hexagonal arrays." Itit. Joint Conference on Neural Networks, vol. II, 119-125, 1989.
61.
Micheli-Tzanakou, E. "Neural Networks in Biomedical Signal Processing," in The Biomedical Engineering Handbook, J. Bronzino, Ed., CRC Press, Inc. Ch 60, pp. 917-931, 1995.
62.
Kirkpatrick, S., Gelatt, C.D., and Vecchi, M.P. "Optimization by Simulated Annealing." Science220:671-679, 1983.
