MetaCartSign in to MyCiteSeer

Include Citations | Advanced Search | Help

Include Citations | Advanced Search | Help

  Classification of Facial Expressions with Domain Gaussian RBF Networks

Download:
Download as a PDF | Download as a PS
by James M. Hogan, Michael Norris, Joachim Diederich
http://sky.fit.qut.edu.au/~hogan/pub/rbfbook.ps.gz
Add To MetaCart

Abstract:

This paper examines the problem of categorisation of facial expressions through the use of a receptive field neural network model, based upon novel domain Gaussian network units trained through error backpropagation. Such networks are trained upon images derived from the Ekman and Friesen "Pictures of Facial Affect " database, and they are subsequently able to successfully generalise to images of unseen subjects, and provide qualitative replication of the perceptual confusions common to previous studies. By using digital morphing techniques to produce intermediate frames between the existing stills, we are able to study the space of transitions between endpoint expressions, our results suggest that expressions unrelated to the endpoint images may be perceived during certain transitions, a path far more complex than direct translation through a neutral expression. 1.

Citations

878 Multilayer feedforward networks are universal approximators – Hornik, Stinchcombe, et al. - 1989
553 Networks for approximation and learning – Poggio, Girosi - 1990
72 Layered neural networks with Gaussian hidden units as universal approximations – Hartman, Keeler, et al. - 1990
55 Unmasking the Face – Ekman, Friesen - 1975
55 Parts and wholes in face recognition – Tanaka, Farah - 1993
51 Miniature language acquisition: A touchstone for cognitive science – Feldman, Lakoff, et al. - 1990
39 Biology and Cognitive Development: The Case of Face Recognition – Johnson, Morton - 1991
33 Speeding up backpropagation – Silva, Almeida - 1990
8 The organization of the cerebral cortex – Sholl - 1956
5 Fast learning in locally-tuned processing units – Moody, Darken - 1989
4 Development of face recognition – Chung, Thomson - 1995
2 Exponential response artificial neurons for pattern classification and function approximation – Geva - 1992
2 Developmental changes in visual scanning of face and nonface patterns by infants – Hainline - 1978
2 Perceptual learning of cartoon faces by young children – Murray, Stanley - 1980
1 Interpretation of facial expressions of affect in children with learning disabilities with verbal or nonverbal deficits – Dimitrovsky, Spector, et al. - 1998
1 The boundaries of words and their meanings". In – Labov - 1973