Particle Swarm Optimization Based Feature Selection for Face Recognition

Dimensionality of extracted feature vectors is one of the main problems in pattern recognition area. In this paper, feature selection using particle swarm optimization (PSO) is proposed and evaluated on face recognition problem. Feature selection can help to reduce the dimensionality of the feature vectors and in chorus maintain the quality of the reserved features. For evaluation purpose, Experiments carried out using two well-known face databases. Performance of the PSO approach in terms of accuracy, specificity and sensitivity show that PSO approach gives high performance compare to other algorithms such as principal component analysis (PCA). The PSO approach can be furtherly studied and generalized for different pattern recognition applications.