期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2018
卷号：18
期号：12
页码：102-110
出版社：International Journal of Computer Science and Network Security
摘要：Texture analysis is widely used in the field of face liveness detection system because of its discriminant properties in differentiating between live and spoof facial samples. Most popular texture descriptor known as LBP and its extended versions had often been used to calculate the texture features for verifying the spoof attacks. However, there are several limitations with LBP and the corresponding extended descriptors. In this paper, we filled the research gap and proposed a new robust texture descriptor, which include local features by Sign, Magnitude and Center complementary components. The threshold value was dynamically set by implementing Weber’s Law for threshold setting. The proposed texture descriptor was used for face liveness detection and through experimental analysis on available face spoof databases it is proved that it outperformed as compare to the stat-of-art texture descriptors.
