Fusing facial shape and appearance based features for robust face recognition

How to describe an image accurately with the most useful information is the key of any face recognition task. In this paper, we argue that robust recognition requires several different kinds of information to be taken into account. Therefore, a new technique that combines the facial shape with the local structure of a face image is proposed, namely fusing shape and appearance features (FSAF). It is based on Gabor wavelets and local edge/corner feature integration (LFI) technique. Given an input image, the Gabor features histogram and LFI histogram are built separately. Then a final feature descriptor is formed by concatenating these two histograms, which feeds to the support vector machine (svm) classifier to recognize the face image. FSAF is evaluated on several challenging face datasets and provided promising results.