An approach for eye detection using parallel genetic algorithm


Talay A.

COMPUTATIONAL SCIENCE - ICCS 2005, PT 3, vol.3516, pp.1004-1007, 2005 (Peer-Reviewed Journal) identifier

  • Publication Type: Article / Article
  • Volume: 3516
  • Publication Date: 2005
  • Journal Name: COMPUTATIONAL SCIENCE - ICCS 2005, PT 3
  • Journal Indexes: Science Citation Index Expanded
  • Page Numbers: pp.1004-1007

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.