Title :
Automatic location of visual features by a system of multilayered perceptrons
Author :
Vincent, J.M. ; Waite, J.B. ; Myers, D.J.
Author_Institution :
British Telecom Labs., Ipswich, UK
fDate :
12/1/1992 12:00:00 AM
Abstract :
A two-stage neural vision system for locating facial features is described. The first stage generates search regions in an image at low spatial resolution and the second pinpoints the features at high resolution. Both stages employ multilayered perceptrons trained to detect specific visual details, followed by sophisticated global postprocessing of their outputs. This work demonstrates the power of combining neural feature detection with knowledge-based context-sensitive methods
Keywords :
computer vision; face recognition; feature extraction; feedforward neural nets; knowledge based systems; MLP; facial features; feature location; global postprocessing; high resolution; knowledge-based context-sensitive methods; low spatial resolution; multilayered perceptrons; neural feature detection; search regions; two-stage neural vision system;
Journal_Title :
Radar and Signal Processing, IEE Proceedings F