16 April 2014 NSCT-based fusion enhancement for multispectral finger-vein images
Author Affiliations +
Proceedings Volume 9159, Sixth International Conference on Digital Image Processing (ICDIP 2014); 91590U (2014) https://doi.org/10.1117/12.2064239
Event: Sixth International Conference on Digital Image Processing, 2014, Athens, Greece
Abstract
Personal identification based on single-spectral finger-vein image has been widely investigated recently. However, in finger-vein imaging, finger-vein image degradation is the main factor causing lower recognition accuracy. So, to improve the finger-vein image quality, in this paper, multispectral finger-vein images (760nm and 850nm) are fused together for contrast enhancement using NSCT transformation. The proposed method can preserve the completeness and sharpness of finger-vein. Experimental results demonstrate that the proposed method is certainly powerful in enhancing finger-vein image contrast and achieves lower equal error rates in finger-vein recognition even if original images have poor contrast.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dongdong Wu, Dongdong Wu, Jinfeng Yang, Jinfeng Yang, "NSCT-based fusion enhancement for multispectral finger-vein images", Proc. SPIE 9159, Sixth International Conference on Digital Image Processing (ICDIP 2014), 91590U (16 April 2014); doi: 10.1117/12.2064239; https://doi.org/10.1117/12.2064239
PROCEEDINGS
5 PAGES


SHARE
Back to Top