Face Anti-Spoofing Algorithm Based On Gray Level Co-Occurrence Matrix And Dual Tree Complex Wavelet Transform

By analyzing the difference of facial texture features between living face and photo, we propose a novel face anti-spoofing algorithm based on gray level co-occurrence matrix (GLCM) and dual-tree complex wavelet tree (DT-CWT). Firstly, inspired by the co-occurrence matrix, we extract five texture features including angle second moment, entropy, contrast, correlation and local uniformity to represent the gray direction, interval and amplitude information for the face texture information. Secondly, DT-CWT has the advantages of approximate translation invariance and good direction selectivity. Therefore, the coefficients of DT-CWT can enhance the texture information and edge information in the frequency domain. At last, the SVM classification is used to distinguish between true and fake face. Our algorithm is demonstrated on the published NUAA database. Compared with the existing methods, the feature dimension is reduced. The experimental results show that the proposed algorithm improves the detection accuracy.