Categorization of faces using unsupervised feature extraction
- 1 January 1990
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 65-70 vol.2
- https://doi.org/10.1109/ijcnn.1990.137696
Abstract
The proposal of G. Cottrell et al. (1987) that their image compression network might be used to extract image features for pattern recognition automatically, is tested by training a neural network to compress 64 face images, spanning 11 subjects, and 13 nonface images. Features extracted in this manner (the output of the hidden units) are given as input to a one-layer network trained to distinguish faces from nonfaces and to attach a name and sex to the face images. The network successfully recognizes new images of familiar faces, categorizes novel images as to their `faceness' and, to a great extent, gender, and exhibits continued accuracy over a considerable range of partial or shifted inputKeywords
This publication has 2 references indexed in Scilit:
- The face pattern identification by back-propagation learning procedureNeural Networks, 1988
- Learning representations by back-propagating errorsNature, 1986