Abstract: Facial expression recognition system using evolutionary particle swarm optimization (PSO)- based feature optimization employs modi?ed local binary patterns, which conduct horizontal and vertical neighborhood pixel comparison, to generate a discriminative initial facial representation. Then, a PSO variant embedded with the concept of a micro genetic algorithm (mGA), called mGA embedded PSO, is proposed to perform feature optimization. It incorporates a nonreplaceable memory, a small-population secondary swarm, a new velocity updating strategy, a subdimension- based in-depth local facial feature search, and a cooperation of local exploitation and global exploration search mechanism to mitigate the premature convergence problem of conventional PSO. Multiple classi?ers are used for recognizing seven facial expressions. Based on a comprehensive study using within- and cross-domain images from the extended Cohn Kanade and MMI benchmark databases, respectively, the empirical results indicate that proposed system outperforms other state-of-the-art PSO variants, conventional PSO, classical GA, and other related facial expression recognition models reported in the literature by a signi?cant margin.

Keywords: Ensemble classi?er, facial expression recognition, feature selection, particle swarm optimization (PSO).