Detection of human faces in color image using genetic algorithm

A genetic approach for human faces detection is proposed. Firstly, the possible facial components are extracted from image, and then the geometry rules are employed to select the candidate eye pairs. Then genetic algorithm is applied to search for possible face regions from candidate eye pairs. The fitness value of each solution is measured based on the information of gray projection and skin-color distribution in face region. Experimental results show that the proposed approach is reliable, and it can detect the frontal human faces with various orientations.