Abstract
Finger vein recognition has been considered one of the most promising biometrics for personal authentication. However, the capacities and percentages of finger tissues (e.g., bone, muscle, ligament, water, fat, etc.) vary person by person. This usually causes poor quality of finger vein images, therefore degrading the performance of finger vein recognition systems (FVRSs). In this paper, the intrinsic factors of finger tissue causing poor quality of finger vein images are analyzed, and an intensity variation (IV) normalization method using guided filter based single scale retinex (GFSSR) is proposed for finger vein image enhancement. The experimental results on two public datasets demonstrate the effectiveness of the proposed method in enhancing the image quality and finger vein recognition accuracy.
Highlights
As a newly emerging biometric, finger vein recognition has attracted significant attention and achieved remarkable development during the last decade
It is clearly shown that single scale retinex (SSR), which is effective for facial image illumination normalization, is not beneficial for enhancing the quality of finger vein when using Discrete wavelet transform (DWT) and LPQ for feature extraction
SSR is beneficial for image enhancement when using LBP for feature extraction, but it fails with usage of DWT and LPQ
Summary
As a newly emerging biometric, finger vein recognition has attracted significant attention and achieved remarkable development during the last decade. FVRSs suffer from external factors such as imaging models [10] and uneven illumination [11,12], and internal factors including scattering [13] and finger tissue [14] These factors cause the finger vein images to become unstable and have low contrast. The contrast between the venous and non-venous regions of the images is poor It was mentioned by Pi et al [14] that tissue structure in different parts of the finger could result in low quality finger vein images. The experimental results obtained for the public datasets MMCBNU_6000 [21] and UTFVP [22] demonstrate that the proposed method can effectively alleviate the intensity variation in finger vein images and enhance the image quality, thereby improving the matching performance.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
