• Bhavesh Rajnikant Joshi

In recent years, face recognition systems have encountered challenges from spoofing attacks, especially 3D mask attacks. This study introduces a new method for 3D mask face verification and anti-spoofing using a flow-attention-based spatio-temporal aggregation network. The goal is to improve the accuracy of face recognition systems by distinguishing real faces from fake ones effectively. The new method uses a special flow-attention mechanism to notice small changes in movement and texture between actual faces and 3D masks. By combining spatial and temporal features, the system gets better at spotting fake attempts. This way of doing things not only makes face verification more accurate but also boosts the system's ability to fight against tricky 3D mask tricks. The method's success is proven through thorough testing and validation.

3D Mask Face Verification and Anti-Spoofing: An Advanced Approach Using Deep Learning

"3D Mask Face Verification and Anti-Spoofing: An Advanced Approach Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.h1-h4, June-2024, Available :http://www.jetir.org/papers/JETIR2406701.pdf

"3D Mask Face Verification and Anti-Spoofing: An Advanced Approach Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. pph1-h4, June-2024, Available at : http://www.jetir.org/papers/JETIR2406701.pdf