Fusion of global and local features for face verification

A personalized feature combination scheme is proposed for face verification. ANFIS (adaptive neuro-fuzzy inference system) and SVM (support vector machine) are adopted respectively to form specialized feature representation for each subject by fusing global and local features. Instead of the common way for different subjects, we realize a new representation that adapts to each individual. Such adaptability in feature selection is inspired by face recognition in the HVS (human visual system) and results in an improved recognition rate.