Abstract
Face recognition has been one of the most studied topics in the last decades. Its research has increased in many applications in communications and automatic access control systems. In this paper, a new face recognition method based on OpenCV face detection technique is introduced. The goal of the propose method is to detect faces that exist in the image and trying to locate each face in a previously prepared database using simple variance calculations and Euclidean distance of extracted facial features. The features under consideration are eyes, nose and mouse. Furthermore, a new method to extract facial features is developed based on feature location with respect to face dimensions. The proposed algorithm has been tested on various images and its performance is found to be good in most cases. Experimental results show that our method of detection and verification achieves very encouraging results with good accuracy and simple computations.