Recognition of human front face in Grayscale Images

Abstract

We propose a new technique to recognize the unknown person in grayscale face images for which the position, scale and image-plane rotation of the face are unknown. The proposed system detects the iris of both eyes and normalizes the position, scale and image-plane rotation of the face using iris positions. The algorithm measures the degree of matching between the image and the face template of each person using normalized crosscorrelation value. Recognition of a human face is done using the highest degree of matching.