Title :
Face recognition using a hybrid supervised/unsupervised neural network
Author :
Intrator, Nathan ; Reisfeld, Daniel ; Yeshurun, Yehezkel
Author_Institution :
Dept. of Comput. Sci., Tel Aviv Univ., Israel
Abstract :
Face recognition schemes that are applied directly to gray level pixel images are presented. Two methods for reducing the overfitting-a common problem in high dimensional classification schemes-are presented and the superiority of their combination is demonstrated. The classification scheme is preceded by preprocessing devoted to reducing the viewpoint and scale variability in the data
Keywords :
face recognition; face recognition; facial normalisation; feature extraction; gray level pixel images; high dimensional classification; hybrid supervised/unsupervised neural network; scale variability; Artificial neural networks; Computer science; Degradation; Face recognition; Image recognition; Neural networks; Pixel; Plastics; Robustness; Unsupervised learning;
Conference_Titel :
Pattern Recognition, 1994. Vol. 2 - Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6270-0
DOI :
10.1109/ICPR.1994.576874
