Deeply learned pore-scale facial features with a large pore-to-pore correspondences dataset

Abstract Similar to fingerprints and irises, pore-scale facial features can be used to distinguish human identities effectively. However, without pore-to-pore correspondenecs dataset, there are no deep learning based methods for pore-scale facial features. AActually, it is hard to establish a large pore-to-pore correspondences dataset due to the existing high-resolution face databases are uncalibrated and nonsynchronous. In this paper, we employ a constraint based on 3D facial model and construct a large pore-to-pore correspondences dataset. This dataset is then used to train a Convolutional Neural Network (CNN) to generate the novel pore-scale facial features - Deeply Learned Pore-scale Facial Features (DLPFF). The experiments show that our learning based method achieves the state-of-the-art matching performance on the Bosphorus facial database and has good generalization.