A Review on Multimodal Face Anti-Spoofing in Multi-layer Environment

With advancement of technology, the need of various threats also increases. One of the key threats is face spoofing, i.e. one can spoof the image of someone’s face image and utilize for unethical purpose. In order to resolve this issue, researchers have suggested the face anti-spoofing techniques. Afterwards, many researchers have suggested and analyzed the techniques to improve upon the basic face anti-spoofing technique. These techniques utilize both local and long-range information. Recently, the researchers propose a new architecture called Conv-MLP that combines local features extracted by CNNs with global information from multilayer perceptrons. Additionally, they suggest using a new loss function called ditch loss to improve the system's ability to generalize to new types of attacks. Thus, in this study we have reviews the available techniques under multi player environments for face anti-spoofing techniques and showcase the pros and cons of the same thing.