Face Detection Using Haar Cascade Classifiers

Bhavana R. Maale, Dr. Suvarna Nandyal

Abstract: The main building block on which all automated systems concerned with human faces are designed is face detection. In many person-system user interfaces, precise face identification is important; the real implication is the precise approach to face identification. This paper proposes, a 3-stage face detection system architecture that is based on the Haar Cascade Classifiers. Pictures of classical Indian kathak and kuchipudi dances are included. In the proposed method, 94 percent of the faces were correctly identified using 1000 images for research.

Keywords: Haar Cascade Classifier, 3-stage face detection, Haar-like features, Adaboost algorithm