This paper introduces the establishment of PolyU near-infrared face database (PolyU-NIRFD) and presents a new coding scheme for face recognition. The PolyU-NIRFD contains images from 350 subjects, each contributing about 100 samples with variations of pose, expression, focus, scale, time, etc. In total, 35,000 samples were collected in the database. The PolyU-NIRFD provides a platform for researchers to develop and evaluate various near-infrared face recognition techniques under large scale, controlled and uncontrolled conditions. A new coding scheme, namely directional binary code (DBC), is then proposed for near-infrared face recognition. Finally, we provide three protocols to evaluate and compare the proposed DBC method with baseline face recognition methods, including Gabor based Eigenface, Fisherface and LBP (local binary pattern) on the PolyU-NIRFD database. In addition, we also conduct experiments on the visible light band FERET database to further validate the proposed DBC scheme.
- Face database
- Feature extraction
- Near-infrared face recognition
ASJC Scopus subject areas
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence