An effective facial spoofing detection approach based on weighted deep ensemble learning

Deep learning has seen successful implementation in various domains, such as natural language processing, image classification, and object detection in recent times. In the field of biometrics, deep learning has also been used to develop effective anti-spoofing systems. Facial spoofing, the act of presenting fake facial information to deceive a biometric system, poses a significant threat to the security of face recognition systems. To address this challenge, we propose, in this paper, an effective and robust facial spoofing detection approach based on weighted deep ensemble learning. Our method combines the strengths of two powerful deep learning architectures, DenseNet201 and MiniVGG. The choice of these two architectures is based on a comparative study between DenseNet201, DenseNet169, VGG16, MiniVGG, and ResNet50, where DenseNet201 and MiniVGG obtained the best recall and precision scores, respectively. Our proposed weighted voting ensemble leverages each architecture-specific capabilities to make the final prediction. We assign weights to each classification model based on its performance, which are determined by a mathematical formulation considering the trade-off between recall and precision. To validate the effectiveness of our proposed approach, we evaluate it on the challenging ROSE-Youtu face liveness detection dataset. Our experimental results demonstrate that our proposed method achieves an impressive accuracy rate of 99% in accurately detecting facial spoofing attacks.