Facial expressions play a key role in identifying the internal emotion state of human beings. Human beings have thetendency to recognize human emotions without any delay. But, a fully automated expression recognition by a computer isa problem that still persists. Towards solving this problem, a Local Optimal Oriented Pattern (LOOP) has been proposedin this paper. This descriptor is proposed to overcome some of the drawbacks in existing feature descriptors, Local BinaryPattern (LBP) and Local Directional Pattern (LDP) by combining the strengths of each of these two descriptors. TheLOOP descriptor has been applied on JAFFE, MUG, WSEFEP and ADFES databases in person independent setup. Theexperiments were conducted for six, seven expressions in all the four databases. The experimental results proved that theproposed LOOP descriptor achieved a better recognition accuracy than existing methods by taking less computation time.
展开▼