In this contribution, human face as biometric [1] is considered. Original method of feature extraction from image data is introduced using MLP (multilayer perceptron) and PCA (principal component analysis). This method is used in human face recognition system and results are compared to face recognition system using PCA directly, to a system with direct classification of input images by MLP and RBF (radial basis function) networks, and to a system using MLP as a feature extractor and MLP and

more »

... networks in the role of classifier. Also a twostage method for face recognition is presented, in which Kohonen self-organizing map is used as a feature extractor. MLP and RBF network are used as classifiers. In order to obtain deeper insight into presented methods, also visualizations of internal representation of input data obtained by neural networks are presented. Miloš ORAVEC received the MSc., PhD. and Assoc. Prof. degrees in telecommunication engineering from the Faculty of Electrical Engineering and Information Technology, Slovak University of Technology (FEI SUT) in Bratislava in 1990Bratislava in , 1996Bratislava in and 2002. He is with the Dept. of Telecommunications, FEI SUT. He is a member of the IET. His research interests include image processing, neural networks and communication networks. Jarmila PAVLOVIČOVÁ received the MSc., PhD. and Assoc. Prof. degrees in telecommunication engineering from the FEI SUT in Bratislava in 1986Bratislava in , 2002Bratislava in and 2006 respectively. She is with the Dept. of Telecommunications, FEI SUT Bratislava. Her research interests include image processing, especially image segmentation.