Face-Spoof Detection using Radon Transform based Statistical Measures

With the rising popularity of biometric traits-based authentication systems, their weaknesses are also grabbing attention of the research communities. This paper introduces a new anti-spoofing scheme for face recognition systems which exploits different measures based on the radon transform. The feature set used in the proposed method consists of five popularly known statistical moments, and uses support vector machine for classification. Extensive simulations are carried out using two different databases to assess the performance of the proposed method. It is found that the proposed method achieves a true recognition rate (TRR) of around 97%, yet maintaining the false acceptance rate (FAR) at around 1%.