PROJECT TITLE :

Lbp Edge-Mapped Descriptor Using Mgm Interest Points For Face Recognition - 2017

ABSTRACT:

In recent years, face recognition has become a common topic in academia and business. Current native ways like the local binary pattern (LBP), and scale invariant feature rework (SIFT) perform higher than holistic methods, but their high complexity levels limit their application. In addition, SIFT-based schemes are sensitive to illumination variation. We tend to propose an LBP edge-mapped descriptor that uses maxima of gradient magnitude (MGM) points. It will completely illustrate facial contours and has low computational complexity. Underneath variable lighting, experimental results show that our proposed method includes a sixteen.5p.c higher recognition rate and requires nine.06 times less execution time than SIFT in the FERET database subset fc. Additionally, when applied to the Extended Yale Face Database B, our method outperformed SIFT-based approaches as well as saving about 70.9% in execution time. Furthermore, in uncontrolled conditions, our technique incorporates a 0.82p.c higher recognition rate than native by-product pattern histogram sequences (LDPHS) within the Unconstrained Facial Images (UFI) database.