Limits...
Intensity Variation Normalization for Finger Vein Recognition Using Guided Filter Based Singe Scale Retinex.

Xie SJ, Lu Y, Yoon S, Yang J, Park DS - Sensors (Basel) (2015)

Bottom Line: 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).The experimental results on two public datasets demonstrate the effectiveness of the proposed method in enhancing the image quality and finger vein recognition accuracy.

View Article: PubMed Central - PubMed

Affiliation: Institute of Remote Sensing and Earth Science, College of Science, Hangzhou Normal University, Hangzhou 311121, China. shanj_x@hotmail.com.

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.

Show MeSH
Outputs of guided filter with different parameters (ε,r). The guidance image is identical to the input image.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541924&req=5

sensors-15-17089-f005: Outputs of guided filter with different parameters (ε,r). The guidance image is identical to the input image.

Mentions: Finger vein images include mostly background but sparsely curves, which may be blurred by any external factor. Through a guided filter, most background regions can be smoothed in their local means, since their variances are relatively small. Meanwhile, since vein curves are covered in region with relatively high variances, their curves also remain as a filtering result, but their intensity become lower due to larger r. Therefore, as shown in Figure 5, when we look at a result of a finger vein image filtered by a guided filter, we can see that it includes most of background smoothed by local means and weak vein curves. When this result is subtracted from its original image by GFSSR process, it contributes on not only removing some intensity variation with smoothing effects but also on reducing blurring effects of curves, as shown in Figure 6.


Intensity Variation Normalization for Finger Vein Recognition Using Guided Filter Based Singe Scale Retinex.

Xie SJ, Lu Y, Yoon S, Yang J, Park DS - Sensors (Basel) (2015)

Outputs of guided filter with different parameters (ε,r). The guidance image is identical to the input image.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541924&req=5

sensors-15-17089-f005: Outputs of guided filter with different parameters (ε,r). The guidance image is identical to the input image.
Mentions: Finger vein images include mostly background but sparsely curves, which may be blurred by any external factor. Through a guided filter, most background regions can be smoothed in their local means, since their variances are relatively small. Meanwhile, since vein curves are covered in region with relatively high variances, their curves also remain as a filtering result, but their intensity become lower due to larger r. Therefore, as shown in Figure 5, when we look at a result of a finger vein image filtered by a guided filter, we can see that it includes most of background smoothed by local means and weak vein curves. When this result is subtracted from its original image by GFSSR process, it contributes on not only removing some intensity variation with smoothing effects but also on reducing blurring effects of curves, as shown in Figure 6.

Bottom Line: 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).The experimental results on two public datasets demonstrate the effectiveness of the proposed method in enhancing the image quality and finger vein recognition accuracy.

View Article: PubMed Central - PubMed

Affiliation: Institute of Remote Sensing and Earth Science, College of Science, Hangzhou Normal University, Hangzhou 311121, China. shanj_x@hotmail.com.

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.

Show MeSH