Improving Face Detection

Authors

Abstract

A novel Genetic Programming approach for the improvement of the performance of classier systems through the synthesis of new training instances is presented. The approach relies on the ability of the Genetic Programming engine to identify and exploit shortcomings of classier systems, and generate instances that are misclassied by them. The addition of these instances to the training set has the potential to improve classier's performance. The experimental results attained with face detection classiers are presented and discussed. Overall they indicate the success of the approach.

Keywords

Evolutionary Computation, Machine Learning

Subject

Artificial Intelligence

Conference

Alberto Moraglio and Sara Silva and Krzysztof Krawiec and Penousal Machado and Carlos Cotta editors, Proceedings of the 15th European Conference on Genetic Programming, EuroGP 2012, volume 7244, pages 73-84, Malaga, Spain, 2012. Springer Verlag, April 2012