作者: Hyunho Kang
DOI: 10.1109/ICCE-BERLIN.2015.7391319
关键词:
摘要: Face recognition is one of the most widely used physiological biometrics. However, a printed photo or smartphone recording face can easily be presented to camera gain illegitimate access system. This paper presents an efficient anti-spoofing approach that detect whether in front genuine fake. The proposed method uses difference between pairwise discrete cosine transform coefficients and logistic regression as machine learning algorithm. experimental results show outperforms local binary patterns method, which representative technique this research field.