Enhanced maximum curvature descriptors for finger vein verification

Munalih Ahmad Syarif, Thian Song Ong, Beng Jin Teoh, Connie Tee

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Maximum Curvature Method (MCM) is one of the promising methods for finger vein verification. MCM scans the curvature of the vein image profiles within a finger for feature extraction. However, the quality of the image can be poor due to variations in illumination and sensor conditions. Furthermore, traditional MCM matching of the vein pattern requires extensive processing time. To address these limitations, we propose an integrated Enhanced Maximum Curvature (EMC) method with Histogram of Oriented Gradient (HOG) descriptor for finger vein verification. Unlike MCM, EMC incorporates an enhancement mechanism to extract small vein delineation that is hardly visible in the extracted vein patterns. Next, HOG is applied instead of image binarization to convert a two-dimensional vein image into a one-dimensional feature vector for efficient matching. The HOG descriptor is able to characterize the local spatial representation of a finger vein by capturing the gradient information effectively. The proposed method is evaluated based on two datasets namely the PKU Finger Vein Database (V4) and SDUMLA-HMT finger vein database. Experiments show promising verification results with equal error rates as low as 0.33 % for DB1 and 0.14 % for DB2 respectively, when EMC+HOG+SVM is applied.

Original languageEnglish
Pages (from-to)6859-6887
Number of pages29
JournalMultimedia Tools and Applications
Volume76
Issue number5
DOIs
Publication statusPublished - 2017 Mar 1

Fingerprint

Feature extraction
Lighting
Sensors
Processing
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Syarif, Munalih Ahmad ; Ong, Thian Song ; Teoh, Beng Jin ; Tee, Connie. / Enhanced maximum curvature descriptors for finger vein verification. In: Multimedia Tools and Applications. 2017 ; Vol. 76, No. 5. pp. 6859-6887.
@article{11763d5f4e89469eb5937030c434fe7c,
title = "Enhanced maximum curvature descriptors for finger vein verification",
abstract = "Maximum Curvature Method (MCM) is one of the promising methods for finger vein verification. MCM scans the curvature of the vein image profiles within a finger for feature extraction. However, the quality of the image can be poor due to variations in illumination and sensor conditions. Furthermore, traditional MCM matching of the vein pattern requires extensive processing time. To address these limitations, we propose an integrated Enhanced Maximum Curvature (EMC) method with Histogram of Oriented Gradient (HOG) descriptor for finger vein verification. Unlike MCM, EMC incorporates an enhancement mechanism to extract small vein delineation that is hardly visible in the extracted vein patterns. Next, HOG is applied instead of image binarization to convert a two-dimensional vein image into a one-dimensional feature vector for efficient matching. The HOG descriptor is able to characterize the local spatial representation of a finger vein by capturing the gradient information effectively. The proposed method is evaluated based on two datasets namely the PKU Finger Vein Database (V4) and SDUMLA-HMT finger vein database. Experiments show promising verification results with equal error rates as low as 0.33 {\%} for DB1 and 0.14 {\%} for DB2 respectively, when EMC+HOG+SVM is applied.",
author = "Syarif, {Munalih Ahmad} and Ong, {Thian Song} and Teoh, {Beng Jin} and Connie Tee",
year = "2017",
month = "3",
day = "1",
doi = "10.1007/s11042-016-3315-4",
language = "English",
volume = "76",
pages = "6859--6887",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "5",

}

Enhanced maximum curvature descriptors for finger vein verification. / Syarif, Munalih Ahmad; Ong, Thian Song; Teoh, Beng Jin; Tee, Connie.

In: Multimedia Tools and Applications, Vol. 76, No. 5, 01.03.2017, p. 6859-6887.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Enhanced maximum curvature descriptors for finger vein verification

AU - Syarif, Munalih Ahmad

AU - Ong, Thian Song

AU - Teoh, Beng Jin

AU - Tee, Connie

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Maximum Curvature Method (MCM) is one of the promising methods for finger vein verification. MCM scans the curvature of the vein image profiles within a finger for feature extraction. However, the quality of the image can be poor due to variations in illumination and sensor conditions. Furthermore, traditional MCM matching of the vein pattern requires extensive processing time. To address these limitations, we propose an integrated Enhanced Maximum Curvature (EMC) method with Histogram of Oriented Gradient (HOG) descriptor for finger vein verification. Unlike MCM, EMC incorporates an enhancement mechanism to extract small vein delineation that is hardly visible in the extracted vein patterns. Next, HOG is applied instead of image binarization to convert a two-dimensional vein image into a one-dimensional feature vector for efficient matching. The HOG descriptor is able to characterize the local spatial representation of a finger vein by capturing the gradient information effectively. The proposed method is evaluated based on two datasets namely the PKU Finger Vein Database (V4) and SDUMLA-HMT finger vein database. Experiments show promising verification results with equal error rates as low as 0.33 % for DB1 and 0.14 % for DB2 respectively, when EMC+HOG+SVM is applied.

AB - Maximum Curvature Method (MCM) is one of the promising methods for finger vein verification. MCM scans the curvature of the vein image profiles within a finger for feature extraction. However, the quality of the image can be poor due to variations in illumination and sensor conditions. Furthermore, traditional MCM matching of the vein pattern requires extensive processing time. To address these limitations, we propose an integrated Enhanced Maximum Curvature (EMC) method with Histogram of Oriented Gradient (HOG) descriptor for finger vein verification. Unlike MCM, EMC incorporates an enhancement mechanism to extract small vein delineation that is hardly visible in the extracted vein patterns. Next, HOG is applied instead of image binarization to convert a two-dimensional vein image into a one-dimensional feature vector for efficient matching. The HOG descriptor is able to characterize the local spatial representation of a finger vein by capturing the gradient information effectively. The proposed method is evaluated based on two datasets namely the PKU Finger Vein Database (V4) and SDUMLA-HMT finger vein database. Experiments show promising verification results with equal error rates as low as 0.33 % for DB1 and 0.14 % for DB2 respectively, when EMC+HOG+SVM is applied.

UR - http://www.scopus.com/inward/record.url?scp=84959158119&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959158119&partnerID=8YFLogxK

U2 - 10.1007/s11042-016-3315-4

DO - 10.1007/s11042-016-3315-4

M3 - Article

AN - SCOPUS:84959158119

VL - 76

SP - 6859

EP - 6887

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 5

ER -