Facial Smile Detection Based on Deep Learning Features

Smile detection from facial images is a specialized task in facial expression analysis with many potential applications such as smiling payment, patient monitoring and photo selection. The current methods on this study are to represent face with low-level features, followed by a strong classifier. However, these manual features cannot well discover information implied in facial images for smile detection. In this paper, we propose to extract high-level features by a well-designed deep convolutional networks (CNN). A key contribution of this work is that we use both recognition and verification signals as supervision to learn expression features, which is helpful to reduce same-expression variations and enlarge different-expression differences. Our method is end-to-end, without complex pre-processing often used in traditional methods. High-level features are taken from the last hidden layer neuron activations of deep CNN, and fed into a soft-max classifier to estimate. Experimental results show that our proposed method is very effective, which outperforms the state-of-the-art methods. On the GENKI smile detection dataset, our method reduces the error rate by 21% compared with the previous best method.