Accurate mouth state estimation via convolutional neural networks

Human mouth is very flexible such that its status (closed or open) is often used as a judgment in the liveness detection of face recognition. However, due to large head pose and illumination variations, accurate mouth status estimation is still challenging in real-world scenarios. In this paper, we propose a deep convolutional neural networks (CNNs) method for mouth status estimation under unconstrained conditions and different types of attacks. Different from previous methods that extract hand-crafted features and then treat the estimation problem as a binary classification task, our method automatically extracts discriminative features via learned convolutional and the pooling layers. To demonstrate the effectiveness of our method and the challenge of mouth status estimation in real-world, we also propose a mouth status estimation dataset that contains 10,714 images in the wild. Experimental results with two types of liveness attacks show that our proposed method outperforms the other traditional methods, especially in the wild condition.