National Changhua University of Education Institutional Repository : Item 987654321/18465
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 6491/11663
造访人次 : 23831839      在线人数 : 115
RC Version 3.2 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 进阶搜寻

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.ncue.edu.tw/ir/handle/987654321/18465

题名: Development of Neural Network Techniques for Finger-Vein Pattern Classification
作者: Wu, Jian-Da;Liu, Chiung-Tsiung;Tsai, Yi-Jang;Liu, Jun-Ching;Chang, Ya-Wen
贡献者: 車輛科技研究所
关键词: Adaptive neuro-fuzzy;Finger-vein pattern classification;Neural network
日期: 2010-02
上传时间: 2014-04-29T07:33:05Z
出版者: SPIE - The International Society for Optical Engineering
摘要: A personal identification system using finger-vein patterns and neural network techniques is proposed in the presentstudy. In the proposed system, the finger-vein patterns are captured by a device that can transmit near infraredthrough the finger and record the patterns for signal analysis and classification. The biometric system for verificationconsists of a combination of feature extraction using principal component analysis and pattern classification usingboth back-propagation network and adaptive neuro-fuzzy inference systems. Finger-vein features are first extractedby principal component analysis method to reduce the computational burden and removes noise residing in thediscarded dimensions. The features are then used in pattern classification and identification. To verify the effect ofthe proposed adaptive neuro-fuzzy inference system in the pattern classification, the back-propagation network iscompared with the proposed system. The experimental results indicated the proposed system using adaptiveneuro-fuzzy inference system demonstrated a better performance than the back-propagation network for personalidentification using the finger-vein patterns.
關聯: The 2nd International Conference on Digital Image Processing, Proc. SPIE, 7546
显示于类别:[車輛科技研究所] 會議論文

文件中的档案:

档案 大小格式浏览次数
2030500216015.pdf25KbAdobe PDF280检视/开启


在NCUEIR中所有的数据项都受到原著作权保护.

 


DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈