A Multi-level Classification Approach for Facial Emotion Recognition

Recognition of facial expressions and infer emotions from them is become increasingly relevant in many commercial and law enforcement applications. In this paper, we present a multi-level classification approach for human emotion recognition from facial images. In the proposed approach, the classification accuracy of principal component analysis (PCA) at level 1 is boosted by Support Vector Machines (SVMs) at level 2. Experimental results demonstrate that the proposed approach can successfully recognize facial emotion with 94% recognition rate.