This Article 
 Bibliographic References 
 Add to: 
A Fast and Accurate Face Detector Based on Neural Networks
January 2001 (vol. 23 no. 1)
pp. 42-53

Abstract—Detecting faces in images with complex backgrounds is a difficult task. Our approach, which obtains state of the art results, is based on a new neural network model: the Constrained Generative Model (CGM). Generative, since the goal of the learning process is to evaluate the probability that the model has generated the input data, and constrained since some counterexamples are used to increase the quality of the estimation performed by the model. To detect side view faces and to decrease the number of false alarms, a conditional mixture of networks is used. To decrease the computational time cost, a fast search algorithm is proposed. The level of performance reached, in terms of detection accuracy and processing time, allows to apply this detector to a real world application: the indexation of images and videos.

[1] P. Baldi and K. Hornik, “Neural Networks and Principal Components Analysis: Learning from Examples without Local Minima,” Neural Networks, vol. 2, pp. 53-58, 1989.
[2] R.J. Baron, “Mechanisms of Human Facial Recognition,” Int'l J. Man Machine Studies, vol. 15, pp. 137-178, 1981.
[3] S. Ben-Yacoub, “Fast Object Detection Using MLP and FFT,” technical report, IDIAP, Martigny, Switzerland, 1997.
[4] O. Bernier, M. Collobert, R. Féraud, V. Lemaire, J.E. Viallet, and D. Collobert, “Multrak: A System for Automatic Multiperson Localization and Tracking in Real-Time,” Proc. Int'l Conf. Image Processing, 1998.
[5] D. Beymer, “Face Recognition under Varying Pose,” technical report, MIT, 1993.
[6] H. Bouattour, F. Fogelman-Soulié, and E. Viennet, “Solving the Human Face Recognition Task Using Neural Nets,” Artificial Neural Networks, vol. 2, pp. 1595-1598, 1992.
[7] R. Brunelli and T. Poggio, "Face Recognition: Features vs. Templates," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 10, pp. 1,042-1,053, Oct. 1993.
[8] K. Choong Yow and R. Cipolla, “Detection of Human Faces under Scales, Orientation, and Viewpoint Variations,” Proc. Int'l Conf. Automatic Face and Gesture Recognition, pp. 295-300, 1996.
[9] M. Collobert, R. Féraud, G. Le Tourneur, O. Bernier, J.E. Viallet, Y. Mahieux, and D. Collobert, “Listen: A System for Locating and Tracking Individual Speaker,” Proc. Second Int'l Conf. Automatic Face and Gesture Recognition, 1996.
[10] A.J. Colmenarez and T.S. Huang, Face Detection and Recognition, pp. 174-185. Springer-Verlag, 1998.
[11] G.W. Cottrell and P. Muro, “Principal Components Analysis of Images via Back Propagation,” SPIE: Visual Comm. and Image Processing, vol. 101, pp. 1070-1077, 1988.
[12] P. Duchnowski, M. Hunke, D. Büsching, U. Meier, and A. Waibel, “Toward Movement-Invariant Automatic Lip-Reading and Speech Recognition,” Proc. Int'l Conf. Spoken Language Processing, pp. 109-112, 1995.
[13] R. Féraud, Face Recognition: From Theory to Applications, Springer-Verlag, vol. 163, pp. 424-432, 1998.
[14] R. Féraud and O. Bernier, “Ensemble and Modular Approaches for Face Detection: A Comparison,” Neural Information Processing System, vol. 10, Dec. 1997.
[15] G.W. Cottrell and M.K. Fleming, "Categorisation of Faces Using Unsupervised Feature Extraction," Proc. Int'l Conf. Neural Networks,San Diego, vol. 2, pp. 65-70, 1990.
[16] S. Geman, E. Bienenstock, and R. Doursat, ”Neural Networks and the Bias/Variance Dilemma,” Neural Computation, vol. 4, pp. 1–58, 1992.
[17] B.A. Golomb, D.T. Lawrence, and T.J. Sejnowski, “Sexnet: A Neural Network Identifies Sex from Human Faces,” Advances in Neural Information Processing Systems, R.P. Lippman, J. Moody, and D.S. Touretzky, eds., vol. 3, pp. 572-577, San Mateo, Calif.: Morgan Kaufmann, 1991.
[18] R. Hoogenboom and M. Lew, “Face Detection Using Local Maxima,” Proc. Int'l Conf. Automatic Face and Gesture Recognition, pp. 334-339, 1996.
[19] J. Huang, S. Gutta, and H. Wechsler, “Detection of Human Faces Using Decision Trees,” Proc. Int'l Conf. Automatic Face and Gesture Recognition, pp. 248-252, 1996.
[20] H.M. Hunke, “Locating and Tracking of Human Faces with Neural Network,” Technical Report CS-94-155, CMU, 1994.
[21] R.A. Jacobs, M.I. Jordan, S.J. Nowlan, and G.E. Hinton, “Adaptative Mixtures of Local Experts,” Neural Computation, vol. 3, pp. 79-87, 1991.
[22] T. Kanade, “Picture Processing by Computer Complex and Recognition of Human Faces,” technical report, Dept. of Computer Science, Kyoto Univ., 1973.
[23] M. Kramer, “Nonlinear Principal Component Analysis Using Autoassociative Neural Networks,” AIChE J., vol. 37, pp. 233-243, 1991.
[24] D. Maio and D. Maltoni, Fast Face Location in Complex Backgrounds, Springer-Verlag, 1998.
[25] B.S. Manjunath, R. Chellappa, and C. von der Malsburg, “A Feature-Based Approach to Face Recognition,” Proc. IEEE Computer Soc. Conf. Computer Vision and Pattern Recognition, pp. 373-378, 1992.
[26] B. Moghaddam and A. Pentland, "Probabilistic Visual Learning for Object Detection," Int'l Conf. Computer Vision, 1995, pp. 786-793.
[27] E. Osuna, R. Freund, and F. Girosi, Training Support Vector Machines: An Application to Face Detection Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 17-19, 1997.
[28] C.P. Papageorgiou, M. Oren, and T. Poggio, “A General Framework for Object Detection,” Proc. Int'l Conf. Computer Vision, pp. 555-562, 1998.
[29] H. Rowley, S. Baluja, and T. Kanade, “Human Face Detection in Visual Scenes,” Neural Information Processing Systems 8, 1995.
[30] H. Rowley, S. Baluja, and T. Kanade, "Neural Network-Based Face Detection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 1, Jan. 1998, pp. 23-38.
[31] R. Séguier, “Human Faces Detection and Tracking in Video Sequences,” Proc. Seventh Portugese on Pattern Recognition, 1995.
[32] Principal Component Analysis. New York: Springer-Verlag, 1986.
[33] K. Sung and T. Poggio, Example-Based Learning for View-Based Human Face Detection, A.I. Memo 1521, C.B.C.L Paper 112, Dec. 1994.
[34] M.J. Swain, C. Frankel, and A. Vassilis, “Weebseer: An Image Search Engine for the World Wide Web,” Computer Vision and Pattern Recognition, 1997.
[35] M. Turk and A. Pentland, “Eigenfaces for Recognition,” J. Cognitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991.
[36] R. Vaillant, C. Monrocq, and Y. Le Cun, Original Approach for the Localisation of Objects in Images IEEE Proc. Visual Image Signal Process., vol. 141, no. 4, Aug. 1994.
[37] V.N. Vapnik, Statistical Learning Theory, John Wiley&Sons, 1998.
[38] E. Viennet, F. Fogelman-Soulié, “Scene Segmentation Using Multiresolution Analysis and MLP,” Artificial Neural Networks, vol. 2, pp. 1599-1602, 1992.
[39] K. Hornik, M. Stinchcombe, and H. White, “Multilayer Feedforward Networks are Universal Approximations,” Neural Networks, vol. 2, pp. 359-366, 1989.
[40] A.L. Yuille, D.S. Cohen, and P.W. Hallinan, "Feature Extraction from Faces Using Deformable Templates," Proc. Computer Vision and Pattern Recognition,San Diego, June 1989.

Index Terms:
Combination of models, face detection, generative models, machine learning, neural networks, projection.
Raphaël Féraud, Olivier J. Bernier, Jean-Emmanuel Viallet, Michel Collobert, "A Fast and Accurate Face Detector Based on Neural Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 1, pp. 42-53, Jan. 2001, doi:10.1109/34.899945
Usage of this product signifies your acceptance of the Terms of Use.