Facial Expression Recognition Using a Novel Regularized Discriminant Analysis with AdaBoost

摘要

This paper presents a novel method for facial expression recognition including happy, disgust, fear, anger, sad, surprise and neutral. The proposed method utilizes a regularized discriminant analysis-based AdaBoost algorithm (RDA-AB) with local Gabor features to recognize the facial expressions. The RDA-AB uses RDA as a learner in the boosting algorithm. The RDA combines the strength of linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA). It solves the small sample size and ill-posed problems suffered from QDA and LDA using a regularization technique. The proposed method also adopts the particle swarm optimization (PSO) algorithm to estimate optimal parameters in RDA. Experimental results show that the performance of the proposed method is excellent when it is compared with that of other facial expression recognition methods.