S Pan is a research student in the School of Engineering and Digital Arts.
Conference or workshop item
Pan, S. and Deravi, F. (2018). Facial Spoofing Detection Using Temporal Texture Co-occurrence. in: 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis (ISBA). USA: IEEE. Available at: https://doi.org/10.1109/ISBA.2018.8311464.Biometric person recognition systems based on facial images are increasingly used in a wide range of applications. However, the potential for face spoofing attacks remains a significant challenge to the security of such systems and finding better means of detecting such presentation attacks has become a necessity. In this paper, we propose a new spoofing detection method, which is based on temporal changes in texture information. A novel temporal texture descriptor is proposed to characterise the pattern of change in a short video sequence named Temporal Co-occurrence Adjacent Local Binary Pattern (TCoALBP). Experimental results using the CASIA-FA, Replay Attack and MSU-MFSD datasets; the proposed method shows the effectiveness of the proposed technique on these challenging datasets.
Shi, P. and Deravi, F. (2017). Facial Action Units for Presentation Attack Detection. in: 2017 Seventh International Conference on Emerging Security Technologies (EST). IEEE. Available at: https://doi.org/10.1109/EST.2017.8090400.This paper is concerned with biometric spoofing detection using the dynamics of natural facial movements as a feature. Facial muscle movement information can be extracted from video sequences and encoded using the Facial Action Coding System (FACS). The proposed feature constructs a Facial Action Units Histogram (FAUH) to encapsulate this information for the detection of biometric presentation attacks without the need for active user cooperation. The performance of the proposed system was tested on two datasets: CASIA-FASD and Replay Attack and produced encouraging results. Further improvements may be possible by integrating this source of information with other indicators for further protecting biometric systems from subversion.