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.