Face recognition using the Weber Local Descriptor

This paper presents a face recognition method using the Weber Local Descriptor (WLD) feature. The WLD consists of differential excitation component and orientation component, which contains abundant local texture information. In our method, we firstly divide face images into a set of sub-regions and extract their WLD features respectively. We introduce the Sobel descriptor to obtain the orientation component. Then each of sub-regions of probe image is recognized by nearest neighborhood method and the results are fused in decision level through voting to yield the final recognition result. The experimental results over ORL and Yale face database verify the effectiveness of our method.