An Efficient Face Normalization Algorithm Based on Eyes Detection

Abstract

This paper presents an effective and efficient face normalization method based on eyes location. The face is rapidly detected based on boosted cascade of simple Haar-like features firstly. Then, the algorithm detects the position of pupils in the face image using the geometric relation between the face and the eyes. Finally, the algorithm normalizes the orientation, the scale and the grayscale of the face image. The experimental results demonstrated that this algorithm can detect and normalize the face image efficiently and accurately. The algorithm can be used in face recognition because the normalized faces can improve the recognition rate.