Title :
Application of neural networks to the categorisation of facial expressions and its clinical significance
Author :
Driscoll, Mike ; Mazumdar, Joy
Author_Institution :
Dept. of Appl. Math., Adelaide Univ., SA
Abstract :
A consistent method for categorising facial expressions involves the finding of a measuring system that allows for separation of different expressions. This paper investigates the application of three types of neural networks (ART2, competitive learning and learning vector quantisation (LVQ) to categorising human facial expressions
Keywords :
ART neural nets; medical signal processing; pattern classification; unsupervised learning; vector quantisation; ART2; clinical significance; competitive learning; emotions; facial expression categorisation; happiness; human facial expressions; learning vector quantisation; neural networks; sadness; Australia; Displays; Humans; Mathematics; Neural networks; Performance analysis; Psychiatry; Shape; Testing; Vectors;
Conference_Titel :
Engineering in Medicine and Biology Society, 1995 and 14th Conference of the Biomedical Engineering Society of India. An International Meeting, Proceedings of the First Regional Conference., IEEE
Conference_Location :
New Delhi
Print_ISBN :
0-7803-2711-X
DOI :
10.1109/RCEMBS.1995.533018
