A New Approach for Face Recognition and Age Classification using LDP

The present paper proposes a novel local texture features on facial images that recognise facial images based on the Morphological primitive patterns with grain components (MPP-g) on a Local Directional Pattern (LDP). A LDP feature is obtained by computing the edge response values in all eight directions at each pixel position and generating a code from the relative strength magnitude. The local descriptor LDP is more consistent in the presence of noise, and illumination changes, since edge response magnitude is more stable than pixel intensity. The present paper proposes Morphological primitive patterns with grain components (MPP-g) which are rotationally and pose invariant for face recognition and age classification. The experimental result on FGnet database images shows the efficacy of the proposed method.