Hybrid Systems for Facial Analysis and Processing Tasks

  • Srinivas Guttat
  • Harry Wechsler
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 42)


We have proposed in this chapter a hybrid architecture for forensic classification and retrieval tasks and we have shown its feasibility using FERET — a large data base of facial images. The specific facial analysis and processing tasks considered herein include (i) surveilling a gallery of images for the presence of specific probes, (ii) contents-based image retrieval (CBIR), (iii) CBIR subject to correct ID (‘match’) displaying specific facial landmarks such as wearing glasses, (iv) gender classification, and (v) ethnic classification. The hybrid architectures, consisting of an ensemble of connectionist networks — radial basis functions (RBF) — and inductive decision trees (DT), combines the merits of ‘holistic’ template matching with those of ‘discrete’ features and classifiers using both positive and negative learning examples. The specific characteristics of our hybrid architecture include (a) query by consensus as provided by ensembles of networks for coping with the inherent variability of the image formation and data acquisition process, (b) categorical classifications using decision trees, and (c) flexible and adaptive thresholds as opposed to ad hoc and hard thresholds.


Radial Basis Function Face Image Neural Information Processing System Class Output Radial Basis Function 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Gudivada, V.N., Raghavan, V.V. (1995): Content-Based Image Retrieval Systems, IEEE Compter18, 18–21CrossRefGoogle Scholar
  2. [2]
    Jain, A. (1992): Final Report to NSF on the Workshop of Visual Information ManagementGoogle Scholar
  3. [3]
    Samal, A., Iyengar, P. (1992): Automatic Recognition and Analysis of Human faces and Facial Expressions: A Survey, Pattern Recognition 25,65–77.CrossRefGoogle Scholar
  4. [4]
    Chellappa, R. Wilson, C.L., Sirohey, S. (1995): Human and Machine Recognition of Faces: A Survey, Proc. IEEE 83, 705–740.CrossRefGoogle Scholar
  5. [5]
    Gutta, S. Wechsler, H. (1997): Face Recognition using Hybrid Classifiers. Pattern Recognition 30(4), 539–553.CrossRefGoogle Scholar
  6. [6]
    Turk, M. Pentland, A. (1991): Eigenfaces for Recognition, J Cognitive Neuroscience 3, 71–86.CrossRefGoogle Scholar
  7. [7]
    Sirohey, S.A. (1993): Human Face Segmentation and Identification, Computer Vision Laboratory, University of Maryland CS-TR-3176Google Scholar
  8. [8]
    Arad, N., Dyn, N., Reisfeld, D., Yeshurun, Y. (1994): Image Warping by Radial Basis Functions: Application to Facial Expressions, CVGIP: Graphical Models and Image Processing 56(2), 161–172CrossRefGoogle Scholar
  9. [9]
    Takacs, B., Wechsler, H. (1995): Face Location Using a Dynamic Model of Retinal Feature Extraction, Proc. of International Workshop on Automatic Face- and Gesture Recognition (IWAFGR), Zurich, Switzerland, 243–247Google Scholar
  10. [10]
    Brunelli, R., Poggio, T. (1993): Face Recognition: Features versus Templates, IEEE Trans. on Pattern Analysis and Machine Intelligence 15(4), 1042–1052CrossRefGoogle Scholar
  11. [11]
    Baron, R.J. (1981): Mechanisms of Human Facial Recognition, International Journal of Man-Machine Studies 15,137–178CrossRefGoogle Scholar
  12. [12]
    Huber, P. J. (1981): Robust statistics, John Wiley, New YorkMATHCrossRefGoogle Scholar
  13. [13]
    Phillips, P.J. (1994) Matching Pursuit Filter Design, Proc. of the International Conference on Pattern Recognition (ICPR), Jerusalem, Isreal, 3,57–61Google Scholar
  14. [14]
    Buhmann, J., Lange, J., Malsburg, C, Vorbruggen, J.C., Wurtz, R.P. (1992): Object Recognition with Gabor Functions in the Dynamic Link Architecture. In: Kosko, B. (Ed.): Neural Networks for Signal Processing, Prentice Hall, New York, 1,121–159Google Scholar
  15. [15]
    Valentin, D., Abdi, H., Toole, A., Cottrell, G.W. (1994): Connectionist Models of Face Processing: A Survey, Pattern Recognition 27( 9), 1209–1230CrossRefGoogle Scholar
  16. [16]
    Golomb, B.A., Lawrence, D.T., Sejnowski, T.J. (1990): SEXNET: A Neural Network Identifies Sex from Human Faces. In: Lippmann, R.P., Moody, J.E., Touretzky, D.S. (Eds.): Advances in Neural Information Processing Systems (NIPS), Morgan Kaufmann, Palo Alto, 3,572–577Google Scholar
  17. [17]
    Brunelli, R., Poggio, T. (1993): Caricatural Effects in Automated Face Perception, Journal of Biological Cybernetics 69, 235–241CrossRefGoogle Scholar
  18. [18]
    Burton, A.M., Bruce, V., Dench, N. (1993): What’s the Difference between Men and Women? Evidence from Facial Measurement, Perception 22,153–176Google Scholar
  19. [19]
    Tamura, S., Kawai, H., Mitsumoto, H. (1996): Male/Female Identification from 8x6 Very Low Resolution Face Images by Neural Network, Pattern Recognition 29(2), 331–335CrossRefGoogle Scholar
  20. [20]
    Wiskott, L. (1997): Phantom Faces for Face Analysis, Pattern Recognition 30(6), 837–846CrossRefGoogle Scholar
  21. [21]
    Bezdek, J.C. (1994): What is Computational Intelligence ?. In: Zurada, J.M., Marks, C, Robinson, J. (Eds.): Computational Intelligence, Prentice Hall, New York, 1–12Google Scholar
  22. [22]
    Medsker, L.R. (1995): Hybrid Intelligent Systems, Kluwer Academic Publishers, MassachusettsMATHCrossRefGoogle Scholar
  23. [23]
    Gallant, S.I. (1988): Connectionist Expert Systems, Communications of the ACM, 31(2), 152–169CrossRefGoogle Scholar
  24. [24]
    Fu, L.M. (1993): Knowledge-based Connectionism for Revising Domain Theories, IEEE Transactions on Systems, Man, and Cybernetics, 23(1), 173–182CrossRefGoogle Scholar
  25. [25]
    Towell, G.G., Shavlik, J.W. (1994): Refining Symbolic Knowledge using Neural Networks. In: Michalski, R.S., Tecuci, G. (Eds.): Machine Learning: A Multistrategy Approach, Morgan Kaufmann, Palo Alto, 4,405–438Google Scholar
  26. [26]
    Hampshire, J. B., Waibel, A. (1992): The Meta-Pi Network: Building Distributed Knowledge Representations for Robust Multisource Pattern Recognition, IEEE Trans, on Pattern Analysis and Machine Intelligence, 14(7), 751–769CrossRefGoogle Scholar
  27. [27]
    Battiti, R., Colla, A.M. (1994): Democracy in Neural Nets: Voting Schemes for Classification, Neural Networks, 7(4), 691–707CrossRefGoogle Scholar
  28. [28]
    Bala, J., Wechsler, H. (1996): Shape Analysis using Multistrategy Learning, Pattern Recognition, 8(3), 67–79Google Scholar
  29. [29]
    Chang, E.I., Lippmann, R.P. (1991): Using Genetic Algorithms to improve Pattern Classification Performance. In: Touretzky, D.S. (Ed.): Advances in Neural Information Processing Systems (NIPS), Morgan Kaufmann, Palo Alto, 2, 380–387Google Scholar
  30. [30]
    Specht, D.F. (1990): Probabilistic Neural Networks, Neural Networks 3,109–118CrossRefGoogle Scholar
  31. [31]
    Pao, Y.H. (1989): Adaptive Pattern Recognition and neural Networks, Addison Wesley, MassachusettsMATHGoogle Scholar
  32. [32]
    Lincoln, W.P., Skrzypek, J. (1990): Synergy of Clustering Multiple Back Propagation Networks. In: Touretzky, D.S. (Ed.): Advances in Neural Information Processing Systems (NIPS), Morgan Kaufmann, Palo Alto, 1,650–657Google Scholar
  33. [33]
    Soulie, F.F., Viennet, E., Lamy, B. (1993): Multi-Modular Neural Network Architectures for Pattern Recognition: Applications in Optical Character Recognition and Human Face Recognition, International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI), 7,487–498.CrossRefGoogle Scholar
  34. [34]
    Robertson, G., Craw, I. (1994): Testing Face Recognition Systems, Image and Vision Computing, 19,609–614CrossRefGoogle Scholar
  35. [35]
    Phillips, P.J., Wechsler, H., Huang, J., Rauss, P. (1998): The FERET Database and Evaluation Procedure for Face Recognition Algorithms, Image and Vision Computing, 5, 36–41Google Scholar
  36. [36]
    Pentland, A., Picard, R.W., Sclaroff, S. (1994): Photobook: Tools for Content-Based Manipulation of Image Databases. In: Proceedings of Storage and retrieval for Image and Video Databases (SPIE), 2(185), 34–37CrossRefGoogle Scholar
  37. [37]
    Nelson, C. (1993): Intelligent Facial Recognition Systems, Final Report prepared for the United States Department of Energy Office of Safeguards and SecurityGoogle Scholar
  38. [38]
    Huang, J., Gutta, S., Wechsler, H. (1996): Detection of Human Faces using Decision Trees, Proc. of 2nd International Conference on Automatic Face and Gesture Recognition (IWAFGR), Killington, Vermont, 248–252Google Scholar
  39. [39]
    Gutta, S., Huang, J., Kakkad V., and Wechsler, H. (1998): Face Surveillance, Proc. of the International Conference on Computer Vision (ICCV), Mumbai, India, 298–303Google Scholar
  40. [40]
    Haykin, S. (1999): Neural Networks, 2nd Edition, Prentice Hall, New JerseyMATHGoogle Scholar
  41. [41]
    Quinlan, J.R. (1986): The Effect of Noise on Concept Learning. In: Michalski, R.S., Carbonell, J.G., Mitchell, T.M. (Eds.): Machine Learning: an Artificial Intelligence Approach, Morgan Kaufmann, Palo Alto, 2,149–166Google Scholar
  42. [42]
    Weiss, S.M., Kulikowski, C.A. (1991): Computer Systems That Learn, Morgan Kaufmann, Palo Alto (1991)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Srinivas Guttat
    • 1
  • Harry Wechsler
    • 2
  1. 1.Philips Reasearch LabsBriarcliff ManorUSA
  2. 2.Department of Computer ScienceGeorge Mason UniversityFairfaxUSA

Personalised recommendations