A multi-expert approach for Wavelet-based Face Detection

In this work we present an upright frontal face detection system based on the multi-resolution analysis of the face. The images are decomposed into frequency sub-bands with different levels decomposition using different wavelets. We propose to use a multi-matcher where each matcher (a Radial Basis Function Support Vector Machine) is trained using a different set of features (a given sub-band or the gray values) projected onto a lower subspace by Laplacian Eigenmaps, the matchers are combined using the ''Sum Rule''. The matcher selection is performed by running Sequential Forward Floating Selection. To speed up the detection, an eye detector is used to find the position of the most probable face. Among these sub-windows only the sub-windows that are classified, by the matcher trained using gray values, as ''face'' are classified by the multi-matcher.