Solving the Human Face Recognition Task using Neural Nets

作者: Hazem Bouattour , Francoise Fogelman Soulié , Emmanuel Viennet

DOI: 10.1016/B978-0-444-89488-5.50164-0

关键词:

摘要: We describe in this paper some neural network architectures designed to identify human faces from a raster image. The proposed networks are based on multi-layer perceptron with shared weights. discuss different hybrid architectures, combining image feature extraction by MLP and classification specialized algorithms such as LVQ, which offer robust performances allow the system detect “intruders”. present results of our architecture large databases varied complexities, containing images taken real-life unconstrained conditions.

参考文章(6)
Garrison W. Cottrell, Extracting features from faces using compression networks: Face, identity, emotion, and gender recognition using holons Connectionist Models#R##N#Proceedings of the 1990 Summer School. pp. 328- 337 ,(1991) , 10.1016/B978-1-4832-1448-1.50039-1
Matthew Turk, Alex Pentland, Face Processing: Models For Recognition visual communications and image processing. ,vol. 1192, pp. 22- 32 ,(1990) , 10.1117/12.969719
Y. Le Cun, L. D. Jackel, H. P. Graf, B. Boser, J. S. Denker, I. Guyon, D. Henderson, R. E. Howard, W. Hubbard, S. A. Solla, Optical Character Recognition and Neural-Net Chips Springer, Dordrecht. pp. 651- 655 ,(1990) , 10.1007/978-94-009-0643-3_33
M. de Bollivier, P. Gallinari, S. Thiria, Multi-Module Neural Networks for Classification Springer, Dordrecht. pp. 777- 780 ,(1990) , 10.1007/978-94-009-0643-3_73