Abstract
In order to improve the performance of a linear autoassociator (which is a neural network model), we explore the use of several preprocessing techniques. The gist of our approach is to store, in addition to the original pattern, one or several pre-processed (i.e. filtered) versions of the patterns to be stored in a neural network. First, we compare the performance of several pre-processing techniques (a plain vanilla version of the autoassociator as a control, a Sobel operator, a Canny-Deriche operator, and a multiscale Canny-Deriche operator) on an example of a pattern completion task using a noise degraded version of a face stored in an autoassociator. We found that the multiscale Canny-Deriche operator gives the best performance of all models. Second, we compare the performance of the multiscale Canny-Deriche operator with the control condition on a pattern completion task of noise degraded versions (with several levels of noise) of learned faces and new faces of the same or another race than the learned faces. In all cases, the multiscale CannyDeriche operator performs significantly better than the control.
Preview
Unable to display preview. Download preview PDF.
References
Kohonen, T.: Associative memory: A system theoretic approach. Springer-Verlag, Berlin. (1977)
Anderson, J.A., Silverstein, J.W., Ritz S.A. and Jones, R.S.: Distinctive features, categorical perception, and probability learning: Some applications of a neural model, Psychological Review, 84,413–451. (1977)
Valentin, D., Abdi, H., O'Toole, A.J.: Categorization and identification of human face images by neural networks: A review of the linear autoassociative and principal component approaches. Journal of Biological Systems, 2, 413–429. (1994)
Valentin, D., Abdi, H., O'Toole, A.J. Cottrell, G.W.: Connectionist models of face processing: A survey. Pattern Recognition, 27, 1209–1230.
Abdi,H.: Les Réseaux de neurones. Presses Universitaires de Grenoble, Grenoble. (1994)
Jia,X. and Nixon,S.: Extending the feature vector for automatic face recognition. IEEE-Transactions on Patterns Analysis and Machine intelligence, 17, (1995)
Deriche, R.: Using canny's Criteria to Derive a Recursively Implemented optimal Edge Detector. International Journal of Computer Vision, 1 (1987) 167–187.
Bourennane, E., Paindavoine, M. and Truchetet, F.: Amélioration du filtre de Canny-Deriche pour la détection des contours sous forme de rampe. Traitement du signal: Recherche, 10 (1993) 297–310.
Mallat, S. and Zhong, Z.; characterization of signal from multiscale edges. IEEEPAMI, 14, (1992) 710–732.
Valentin, D., Abdi, H.: Can a linear autoassociator recognize faces from new orientations? Journal of the Optical Society of America, series A, 13, 717–724. (1996)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yang, F., Paindavoinei, M., Abdi, H. (1997). A pre-processing technique based on the wavelet transform for linear autoassociators with applications to face recognition. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020271
Download citation
DOI: https://doi.org/10.1007/BFb0020271
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive