Abstract | ||
---|---|---|
Facial expressions are an important source of information for human interaction. Therefore, it would be desirable if computers
were able to use this information to interact more naturally with the user. However, facial expressions are not always unambiguously
interpreted even by competent humans. Consequently, soft computing techniques in which interpretations are given some degree
of support would seem appropriate. This paper describes how the mass assignment approach to constructing fuzzy sets from probability
distributions has been applied to i) the low-level classification of pixels into facial feature classes based on their colour
to segment a facial image into possible facial feature regions, ii) to make a final decision on which combination of these
regions correctly extracts the facial features, and iii) to generate rules which classify the emotional content of the image
according to values taken from these extracted regions.
|
Year | DOI | Venue |
---|---|---|
2000 | 10.1007/10720181_14 | Intelligent Systems and Soft Computing |
Keywords | Field | DocType |
machine interpretation,facial expressions,facial expression | Information system,Computer science,Fuzzy set,Probability distribution,Artificial intelligence,Soft computing,Facial recognition system,Computer vision,Pattern recognition,Facial expression,Pixel,User interface,Machine learning | Conference |
ISBN | Citations | PageRank |
3-540-67837-9 | 1 | 0.43 |
References | Authors | |
6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simon J. Case | 1 | 1 | 0.43 |
James F. Baldwin | 2 | 21 | 9.31 |
Trevor P. Martin | 3 | 134 | 26.98 |