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
ROC curves of different image enhancement methods on UTFVP using different feature extraction algorithms: (a) DWT method; (b) LBP method; and (c) LPQ method.
© Copyright Policy
Related In: Results  -  Collection

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

sensors-15-17089-f012: ROC curves of different image enhancement methods on UTFVP using different feature extraction algorithms: (a) DWT method; (b) LBP method; and (c) LPQ method.

Mentions: For UTFVP, two finger vein images from one individual were selected as the training set, while the remaining two images were used as the test set. The number of genuine and imposter matches are 720(360 × 2) and 258,480(360 × 359 × 2), respectively. Figure 12 shows the ROC curves using DWT, LBP, and LPQ for feature extraction and the corresponding EER values and improved ratios are listed in Table 2.


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)

ROC curves of different image enhancement methods on UTFVP using different feature extraction algorithms: (a) DWT method; (b) LBP method; and (c) LPQ method.
© Copyright Policy
Related In: Results  -  Collection

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

sensors-15-17089-f012: ROC curves of different image enhancement methods on UTFVP using different feature extraction algorithms: (a) DWT method; (b) LBP method; and (c) LPQ method.
Mentions: For UTFVP, two finger vein images from one individual were selected as the training set, while the remaining two images were used as the test set. The number of genuine and imposter matches are 720(360 × 2) and 258,480(360 × 359 × 2), respectively. Figure 12 shows the ROC curves using DWT, LBP, and LPQ for feature extraction and the corresponding EER values and improved ratios are listed in Table 2.

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