An approach for eye detection using parallel genetic algorithm

Abstract

In this paper, a new reliable method for detecting human eyes in an arbitrary image is devised. The approach is based on searching the eyes with Parallel Genetic Algorithm. As the genetic algorithm is a computationally intensive process, the searching space for possible face regions is limited to possible eye regions so that the required timing is greatly reduced. The algorithm works on complex images without constraints on the background, skin color segmentation and so on. The eye detection process works predictably, fairly, reliably and regardless of the perspective. © Springer-Verlag Berlin Heidelberg 2005.