Automatic Facial Expression Recognition—A Circumcenter–Incenter–Centroid (CIC) Trio Feature-Induced Approach

Facial expression is directly related to the changes in the shape of a face. The Active Appearance Model (AAM) can be used to determine the geometrical position of basic components by earmarking landmark points. The landmark points which are congruent upon the basic facial expressions are considered for the generation of triangle set encompassing the face. In this context, the area of the triangle formed by connecting the Circumcenter, Incenter, and Centroid is considered as the key shape descriptor. This novel feature is learned with Multi-Layer Perceptron (MLP) for the classification of expressions in six atomic classes viz Anger, Disgust, Fear, Happiness, Sadness, and Surprise. The proposed system is tested on four well-known benchmark databases viz. I. The Extended Cohn–Kanade (CK+) II. Japanese Female Facial Expression (JAFFE) III. Multimedia Imaging (MMI) and, IV. Multimedia Understanding Group (MUG) database. Overwhelming impressive results on these four databases confirm the effectiveness and efficiency of our proposed method.