Genetic algorithms for classifiers training sets optimisation applied to human face recognition

Human face recognition is a multi-stage process within which many classification problems must be solved. This is performed by learning machines which elaborate classification rules based on a given training set. Therefore, one of the most important issues is selection of a training set which would properly represent the data that will be further classified. This paper presents an approach which utilizes genetic algorithms for selecting classifiers' training sets. This approach was implemented for the Support Vector Machines which is applied in two areas of automatic human face recognition: face verification and feature vectors comparison. Effectiveness of the presented concept was confirmed with appropriate experiments which results are described in this paper.