Towards unconstrained face recognition from image sequences
- 23 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 224-229
- https://doi.org/10.1109/afgr.1996.557268
Abstract
The paper presents experiments using a radial basis function (RBF) network to tackle the unconstrained face recognition problem using low resolution video information. Input representations that mimic the effects of receptive field functions found at various stages of the human vision system were used with RBF network; that learnt to classify and generalise over different views of each person to be recognised. In particular, Difference of Gaussian (DoG) filtering and Gabor wavelet analysis are compared for face recognition from an image sequence. RBF techniques are shown to provide excellent levels of performance where the view varies and the authors discuss how to relax constraints on data capture and improve preprocessing to obtain an effective scheme for real-time, unconstrained face recognition.Keywords
This publication has 12 references indexed in Scilit:
- Probabilistic visual learning for object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Face Recognition using Radial Basis Function Neural NetworksPublished by British Machine Vision Association and Society for Pattern Recognition ,1996
- Invariance in radial basis function neural networks in human face classificationNeural Processing Letters, 1995
- View-based and modular eigenspaces for face recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Face recognition: features versus templatesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Some extensions of radial basis functions and their applications in artificial intelligenceComputers & Mathematics with Applications, 1992
- Networks for approximation and learningProceedings of the IEEE, 1990
- Fast Learning in Networks of Locally-Tuned Processing UnitsNeural Computation, 1989
- Complete discrete 2-D Gabor transforms by neural networks for image analysis and compressionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Theory of edge detectionProceedings of the Royal Society of London. B. Biological Sciences, 1980