Abstract
Similar to fingerprints and irises, pore-scale facial features can be used to distinguish human identities effectively. However, without pore-to-pore correspondences dataset, there are no deep learning based methods for pore-scale facial features. Actually, 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.
Original language | English |
---|---|
Pages (from-to) | 247-254 |
Number of pages | 8 |
Journal | Pattern Recognition Letters |
Volume | 129 |
DOIs | |
Publication status | Published - Jan 2020 |
Keywords
- Deep learning
- Pore-scale facial features
- Pore-scale patch dataset
ASJC Scopus subject areas
- Software
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence