Human face classification for security system

Abstract

We propose a method for classifying faces that uses only simple image processing. The method can rapidly judge whether the person detected by a monitor camera is masked or not. Our algorithm has two stages. The first stage detects the facial pattern by template matching with a new similarity assessment. The second stage judges whether the face is masked or not by using optimal features in the spatial frequency domain. Indeed, experiments show that our algorithm can form an effective security system.