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

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

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, ther...

Full description

Bibliographic Details
Main Authors: Shan Juan Xie, Yu Lu, Sook Yoon, Jucheng Yang, Dong Sun Park
Format: Article
Language:English
Published: MDPI AG 2015-07-01
Series:Sensors
Subjects:
intensity variation
finger vein recognition
image enhancement
guided filter
single scale retinex
Online Access:http://www.mdpi.com/1424-8220/15/7/17089
id doaj-ce7d3ba9f8a74e6fb23c391d20c19865
record_format Article
spelling doaj-ce7d3ba9f8a74e6fb23c391d20c198652020-11-24T22:21:23ZengMDPI AGSensors1424-82202015-07-01157170891710510.3390/s150717089s150717089Intensity Variation Normalization for Finger Vein Recognition Using Guided Filter Based Singe Scale RetinexShan Juan Xie0Yu Lu1Sook Yoon2Jucheng Yang3Dong Sun Park4Institute of Remote Sensing and Earth Science, College of Science, Hangzhou Normal University, Hangzhou 311121, ChinaDivision of Electronic and Information Engineering, Chonbuk National University, Jeonju561-756, KoreaDepartment of Multimedia Engineering, Mokpo National University, Jeonnam534-729, KoreaCollege of Computer Science and Information Engineering, Tianjin University of Science and Technology, Tianjin 300222, ChinaDivision of Electronic and Information Engineering, Chonbuk National University, Jeonju561-756, KoreaFinger 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.http://www.mdpi.com/1424-8220/15/7/17089intensity variationfinger vein recognitionimage enhancementguided filtersingle scale retinex
collection DOAJ
language English
format Article
sources DOAJ
author Shan Juan Xie
Yu Lu
Sook Yoon
Jucheng Yang
Dong Sun Park
spellingShingle Shan Juan Xie
Yu Lu
Sook Yoon
Jucheng Yang
Dong Sun Park
Intensity Variation Normalization for Finger Vein Recognition Using Guided Filter Based Singe Scale Retinex
Sensors
intensity variation
finger vein recognition
image enhancement
guided filter
single scale retinex
author_facet Shan Juan Xie
Yu Lu
Sook Yoon
Jucheng Yang
Dong Sun Park
author_sort Shan Juan Xie
title Intensity Variation Normalization for Finger Vein Recognition Using Guided Filter Based Singe Scale Retinex
title_short Intensity Variation Normalization for Finger Vein Recognition Using Guided Filter Based Singe Scale Retinex
title_full Intensity Variation Normalization for Finger Vein Recognition Using Guided Filter Based Singe Scale Retinex
title_fullStr Intensity Variation Normalization for Finger Vein Recognition Using Guided Filter Based Singe Scale Retinex
title_full_unstemmed Intensity Variation Normalization for Finger Vein Recognition Using Guided Filter Based Singe Scale Retinex
title_sort intensity variation normalization for finger vein recognition using guided filter based singe scale retinex
publisher MDPI AG
series Sensors
issn 1424-8220
publishDate 2015-07-01
description 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.
topic intensity variation
finger vein recognition
image enhancement
guided filter
single scale retinex
url http://www.mdpi.com/1424-8220/15/7/17089
work_keys_str_mv AT shanjuanxie intensityvariationnormalizationforfingerveinrecognitionusingguidedfilterbasedsingescaleretinex
AT yulu intensityvariationnormalizationforfingerveinrecognitionusingguidedfilterbasedsingescaleretinex
AT sookyoon intensityvariationnormalizationforfingerveinrecognitionusingguidedfilterbasedsingescaleretinex
AT juchengyang intensityvariationnormalizationforfingerveinrecognitionusingguidedfilterbasedsingescaleretinex
AT dongsunpark intensityvariationnormalizationforfingerveinrecognitionusingguidedfilterbasedsingescaleretinex
_version_ 1725771477583659008

Similar Items