Abstract:
Face recognition is considered as one of the hottest research areas in computer vision field. The purpose of the proposed research work is to develop an algorithm that can recognize a person by comparing the characteristics of his/her face, which may have expressions, glasses and/or rotation, to those of known faces in a database. This work provides a simple and efficient technique to recognize human faces. The new method is based on variance estimation of the three components of the color faces images and facial features extraction of the most facial features. The features under consideration are eyes, nose and mouth. The technique used to extract facial features was developed based on feature location with respect to face dimensions. The proposed algorithm has been tested on various face images and its performance was found to be good in most cases. Experimental results show that our method of human face recognition achieves very encouraging results with good accuracy, great speed and simple computations.