Abstract

A novel face recognition algorithm using the RBF network is proposed based on the Adaptively Weighted local Muti-channel Gabor Filters (AWMGF). The normalized face image is firstly sampled and blocked, and then the blocked face image was filtered by multi-orientation Gabor filters with multi-scale to extract their corresponding Local Gabor Magnitude Map (LGMM), which were constructed to higher dimensional feature vectors. Next, in order to perform matching in the sense of the richness of identity information and to handle the partial occlusion problem, the proposed algorithm employs an adaptively weighting map to weight the LGMM extracted from local areas based on the contribution of each sub-pattern to the final similarity measurement. Finally, the weighted LGMM is classified by RBF. The Experimental results on the ORL face database and YALE face database show that the proposed method is feasible and higher recognition performance.

Paper Details