Title :
A neural-network approach for compact multi-level representation of human faces
Author :
Grudin, M.A. ; Lisboa, P.J.G. ; Harvey, D.M.
Author_Institution :
Liverpool John Moores Univ., UK
Abstract :
The authors aim to represent a facial image in a hierarchical manner, extract the most remarkable features on each scale, and select only those which remain most stable for different appearances. This may be used to solve a problem indicated by Mallat (1996) concerning the integration of high-level information into a low-level representation. The subordinate advantage of this recognition scheme is a compact face representation, which allows for the reduced database size and faster performance
Keywords :
neural nets; compact face representation; compact multi-level representation; database size; feature extraction; hierarchical facial image representation; high-level information; human faces; low-level representation; neural network approach; performance;
Conference_Titel :
Artificial Neural Networks, Fifth International Conference on (Conf. Publ. No. 440)
Conference_Location :
Cambridge
Print_ISBN :
0-85296-690-3
DOI :
10.1049/cp:19970699
