Face Authentication by retinotopic sampling of the Gabor decomposition and Support Vector Machines
Fabrizio Smeraldi, N. Capdevielle, Josef Bigün · 1999
We describe a face authentication algorithm based on retinotopic sampling of the Gabor decomposition. A log--polar sampling grid is used to encode information from relevant regions of the face. Decision is based on a multi expert scheme, in which each expert independently authenticates the client based on a different facial feature. Implementation of the expert as Support Vector Machines is discussed. An alternative implementation using K--Nearest--Neighbours classifiers is presented for comparison. 1 Introduction As services which require automatic access of eligible persons (clients) to services (privileges) become increasingly common, the importance of face authentication has been growing. Neurological investigations have shown a strong analogy between the responses of the simple cells in the Visual Cortex and a classic and powerful computer vision tool, the Gabor decomposition [13]. Some aspects of the human visual information processing have been captured by the elastic graph ma...