Development of neural network techniques for finger-vein pattern classification

Jian-Da Wu, Chiung Tsiung Liu, Yi Jang Tsai, Jun Ching Liu, Ya Wen Chang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A personal identification system using finger-vein patterns and neural network techniques is proposed in the present study. In the proposed system, the finger-vein patterns are captured by a device that can transmit near infrared through the finger and record the patterns for signal analysis and classification. The biometric system for verification consists of a combination of feature extraction using principal component analysis and pattern classification using both back-propagation network and adaptive neuro-fuzzy inference systems. Finger-vein features are first extracted by principal component analysis method to reduce the computational burden and removes noise residing in the discarded dimensions. The features are then used in pattern classification and identification. To verify the effect of the proposed adaptive neuro-fuzzy inference system in the pattern classification, the back-propagation network is compared with the proposed system. The experimental results indicated the proposed system using adaptive neuro-fuzzy inference system demonstrated a better performance than the back-propagation network for personal identification using the finger-vein patterns.

Original languageEnglish
Title of host publication2nd International Conference on Digital Image Processing
Volume7546
DOIs
Publication statusPublished - 2010 Mar 22
Event2nd International Conference on Digital Image Processing - Singapore, Singapore
Duration: 2010 Feb 262010 Feb 28

Other

Other2nd International Conference on Digital Image Processing
CountrySingapore
CitySingapore
Period10-02-2610-02-28

Fingerprint

Pattern Classification
Veins
Fuzzy inference
Backpropagation
veins
Adaptive Neuro-fuzzy Inference System
Pattern recognition
Back Propagation
Neural Networks
Neural networks
Principal component analysis
Principal Component Analysis
inference
Adaptive systems
Signal analysis
Biometrics
Signal Analysis
principal components analysis
Feature extraction
Identification (control systems)

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Wu, J-D., Liu, C. T., Tsai, Y. J., Liu, J. C., & Chang, Y. W. (2010). Development of neural network techniques for finger-vein pattern classification. In 2nd International Conference on Digital Image Processing (Vol. 7546). [75460F] https://doi.org/10.1117/12.852799
Wu, Jian-Da ; Liu, Chiung Tsiung ; Tsai, Yi Jang ; Liu, Jun Ching ; Chang, Ya Wen. / Development of neural network techniques for finger-vein pattern classification. 2nd International Conference on Digital Image Processing. Vol. 7546 2010.
@inproceedings{4ffeacd450234d4aaaee41c369aa39bd,
title = "Development of neural network techniques for finger-vein pattern classification",
abstract = "A personal identification system using finger-vein patterns and neural network techniques is proposed in the present study. In the proposed system, the finger-vein patterns are captured by a device that can transmit near infrared through the finger and record the patterns for signal analysis and classification. The biometric system for verification consists of a combination of feature extraction using principal component analysis and pattern classification using both back-propagation network and adaptive neuro-fuzzy inference systems. Finger-vein features are first extracted by principal component analysis method to reduce the computational burden and removes noise residing in the discarded dimensions. The features are then used in pattern classification and identification. To verify the effect of the proposed adaptive neuro-fuzzy inference system in the pattern classification, the back-propagation network is compared with the proposed system. The experimental results indicated the proposed system using adaptive neuro-fuzzy inference system demonstrated a better performance than the back-propagation network for personal identification using the finger-vein patterns.",
author = "Jian-Da Wu and Liu, {Chiung Tsiung} and Tsai, {Yi Jang} and Liu, {Jun Ching} and Chang, {Ya Wen}",
year = "2010",
month = "3",
day = "22",
doi = "10.1117/12.852799",
language = "English",
isbn = "9780819479426",
volume = "7546",
booktitle = "2nd International Conference on Digital Image Processing",

}

Wu, J-D, Liu, CT, Tsai, YJ, Liu, JC & Chang, YW 2010, Development of neural network techniques for finger-vein pattern classification. in 2nd International Conference on Digital Image Processing. vol. 7546, 75460F, 2nd International Conference on Digital Image Processing, Singapore, Singapore, 10-02-26. https://doi.org/10.1117/12.852799

Development of neural network techniques for finger-vein pattern classification. / Wu, Jian-Da; Liu, Chiung Tsiung; Tsai, Yi Jang; Liu, Jun Ching; Chang, Ya Wen.

2nd International Conference on Digital Image Processing. Vol. 7546 2010. 75460F.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Development of neural network techniques for finger-vein pattern classification

AU - Wu, Jian-Da

AU - Liu, Chiung Tsiung

AU - Tsai, Yi Jang

AU - Liu, Jun Ching

AU - Chang, Ya Wen

PY - 2010/3/22

Y1 - 2010/3/22

N2 - A personal identification system using finger-vein patterns and neural network techniques is proposed in the present study. In the proposed system, the finger-vein patterns are captured by a device that can transmit near infrared through the finger and record the patterns for signal analysis and classification. The biometric system for verification consists of a combination of feature extraction using principal component analysis and pattern classification using both back-propagation network and adaptive neuro-fuzzy inference systems. Finger-vein features are first extracted by principal component analysis method to reduce the computational burden and removes noise residing in the discarded dimensions. The features are then used in pattern classification and identification. To verify the effect of the proposed adaptive neuro-fuzzy inference system in the pattern classification, the back-propagation network is compared with the proposed system. The experimental results indicated the proposed system using adaptive neuro-fuzzy inference system demonstrated a better performance than the back-propagation network for personal identification using the finger-vein patterns.

AB - A personal identification system using finger-vein patterns and neural network techniques is proposed in the present study. In the proposed system, the finger-vein patterns are captured by a device that can transmit near infrared through the finger and record the patterns for signal analysis and classification. The biometric system for verification consists of a combination of feature extraction using principal component analysis and pattern classification using both back-propagation network and adaptive neuro-fuzzy inference systems. Finger-vein features are first extracted by principal component analysis method to reduce the computational burden and removes noise residing in the discarded dimensions. The features are then used in pattern classification and identification. To verify the effect of the proposed adaptive neuro-fuzzy inference system in the pattern classification, the back-propagation network is compared with the proposed system. The experimental results indicated the proposed system using adaptive neuro-fuzzy inference system demonstrated a better performance than the back-propagation network for personal identification using the finger-vein patterns.

UR - http://www.scopus.com/inward/record.url?scp=77949481663&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949481663&partnerID=8YFLogxK

U2 - 10.1117/12.852799

DO - 10.1117/12.852799

M3 - Conference contribution

AN - SCOPUS:77949481663

SN - 9780819479426

VL - 7546

BT - 2nd International Conference on Digital Image Processing

ER -

Wu J-D, Liu CT, Tsai YJ, Liu JC, Chang YW. Development of neural network techniques for finger-vein pattern classification. In 2nd International Conference on Digital Image Processing. Vol. 7546. 2010. 75460F https://doi.org/10.1117/12.852799