Abstract
This paper proposes a Noise Adaptive Binary Pattern (NABP) for facial image analysis such as face recognition, expression recognition and gender classification. NABP encodes the face microstructures using an adaptive threshold and generates more discriminative patterns than other existing local feature descriptors. Rigorous experiments on two well-known datasets, LFW and CK+, for three different aforementioned applications demonstrate the excellence of NABP as compared to the current state of the art methods.