Analyzing Wavelets Components to Perform Face Recognition
Face recognition is a very difficult task in real environments. In those cases a good preprocessing of the images is needed to keep the images invariant to translations, scales, luminosity, shape, aspect, rotation, noise, etc ... Wavelet transformation have been probed to be a good preprocessing method for many task. However, not all the coefficients of a wavelet transform have the information needed for a classification method to be efficient. This work introduce a method to select the most appropriate coefficients for a wavelet transform to allow an unsupervised neural network to well classify a set of complex faces.
KeywordsFace Recognition Wavelet Transformation Entropy Module Competitive Layer Automatic Face Recognition
Unable to display preview. Download preview PDF.
- 3.A. Carpintero, J. Castellanos, J. Rios, and J. Segovia. Automatic face recognition for access control. In Proceedings of 1993 IJCNN, pages 1289–1292. International Joint Conference on Neural Networks, 1993.Google Scholar
- 6.P. Isasi. Sistema Neuronal Sensible al Entorno con Arquitectura Autoorganizada. PhD thesis, Facultad de Inform'atica, Universidad Polit'ecnica, Madrid, 1994.Google Scholar
- 7.P. Isasi and J. Segovia. Sensitivity analysis in art models: An application in forecasting. In XV International Symposium on Forecasting, Toronto, Canada, June 1995.Google Scholar
- 10.Sheng Liu, R. Olivia, Chih-Ping Wei, and Paul Jen-Hwa Hu. Neural net learning for intelligent patient-image retrieval. IEEE Expert, 13(1):49–57, February 1998.Google Scholar
- 12.D. Rumelhart and McClelland. Parallel Distributed Processing:Explorations in the Microstructure of Cognition, volume II. MIT Press., Cambridge, 1986.Google Scholar