Paper Title
Face Spoofing Detection

Abstract
In this paper we are intended to develop an efficient face spoof detection system using features like chromatic moment and color diversity features. Spoofing is defined as the act of faking the identity of a valid user. Nowadays face recognition systems are increasingly affected by spoofing attacks. The algorithm which we have proposed are very much adequate for face anti-spoofing. A real face displays certain facial behaviors compared to the spoofed one. Spoofing causes distortions in the image quality, which is highly reflected in measuring the chromaticity and color distortions in the given input image. NUAA photograph imposter database is used for the work. Face detection and normalization are applied to the dataset. Thus make the data suitable for applying the anti-spoofing algorithm. The performance of the system measured by using a neural network classifier and decision tree classifier. The accuracy of the proposed system is about 98%. Keywords - Face Spoof Detection, Chromatic Moment, Color Diversity, Face Detection, Face Normalization, Haar Cascade Classifier, Convolutional Neural Network