• S. LOGESH
• A. KRISTIAN
• E. MADHANAKAVI
• A. KANNAN

In this paper, we propose a novel approach for face anti-spoofing detection utilizing recurrent neural networks (RNNs). The proposed method comprises a comprehensive processing pipeline consisting of image acquisition, preprocessing, feature extraction, feature fusion, and classification. Specifically, we employ RNNs, along with Rotation-Invariant Local Binary Patterns (RI-LBP) and Weber Local Descriptors (WLD), for feature extraction. The extracted features are then fused to capture both spatial and temporal information effectively. Finally, a classification model based on RNN is employed to discern between genuine and spoofed faces. Experimental results demonstrate the effectiveness of the proposed method in detecting face-spoofing attempts with high accuracy and robustness.

"ENHANCED FACE ANTI-SPOOFING DETECTION: LEVERAGING STEMMER FEATURES AND RECURRENT NEURAL NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.q159-q164, April-2024, Available :http://www.jetir.org/papers/JETIR2404H23.pdf

"ENHANCED FACE ANTI-SPOOFING DETECTION: LEVERAGING STEMMER FEATURES AND RECURRENT NEURAL NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppq159-q164, April-2024, Available at : http://www.jetir.org/papers/JETIR2404H23.pdf