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

Xianxian Zeng, Xiaodong Wang, Kairui Chen, Dong Li, Yun Zhang, Kin Man Lam

Research output: Journal article publicationJournal articleAcademic researchpeer-review

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 languageEnglish
Pages (from-to)247-254
Number of pages8
JournalPattern Recognition Letters
Volume129
DOIs
Publication statusPublished - 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

Cite this