Embedded fingerprint identification system based on DSP

Weihua Xie; Jie Tian; Xin Yang; Hong Chen; Yuliang He; Tanghui Zhang

doi:10.1117/12.603234

Embedded fingerprint identification system based on DSP

Weihua Xie
, Jie Tian^*
, Xin Yang
, Hong Chen
, Yuliang He
, Tanghui Zhang

^*此作品的通讯作者

University of Chinese Academy of Sciences

科研成果: 期刊稿件 › 会议文章 › 同行评审

摘要

Fingerprint recognition is implemented on Ti DSP chip Ti 5402. The algorithm is prompt and practicable. Enhance part adopts a fast orientation filter to improve inputting image quality combining fast orientation interpolation method. On the other hand, the orientation field is used in fingerprint image segment. Matching part uses point match method and combines some post-processing in order to get good match result. One fusion way is introduced in enrollment. In DSP implement phase, the system frame adopts one kind of dispatched system structure aiming at the 5402 features. Otherwise the algorithm of fingerprint recognition is modified and optimized based on DSP instructions. Experiment result indicates that system performance is good.

源语言	英语
文章编号	41
页（从-至）	363-372
页数	10
期刊	Proceedings of SPIE - The International Society for Optical Engineering
卷	5779
DOI	https://doi.org/10.1117/12.603234
出版状态	已出版 - 2005
已对外发布	是
活动	Biometric Technology for Human Identification II - Orlando, FL, 美国期限: 28 3月 2005 → 29 3月 2005

访问文件

10.1117/12.603234

其它文件与链接

链接到 Scopus 的出版物

引用此

@article{8bb04b47bf374ee6ba0e5dba86123594,

title = "Embedded fingerprint identification system based on DSP",

abstract = "Fingerprint recognition is implemented on Ti DSP chip Ti 5402. The algorithm is prompt and practicable. Enhance part adopts a fast orientation filter to improve inputting image quality combining fast orientation interpolation method. On the other hand, the orientation field is used in fingerprint image segment. Matching part uses point match method and combines some post-processing in order to get good match result. One fusion way is introduced in enrollment. In DSP implement phase, the system frame adopts one kind of dispatched system structure aiming at the 5402 features. Otherwise the algorithm of fingerprint recognition is modified and optimized based on DSP instructions. Experiment result indicates that system performance is good.",

keywords = "DSP, Embedded system, Fingerprint identification, Optimization",

author = "Weihua Xie and Jie Tian and Xin Yang and Hong Chen and Yuliang He and Tanghui Zhang",

year = "2005",

doi = "10.1117/12.603234",

language = "英语",

volume = "5779",

pages = "363--372",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Biometric Technology for Human Identification II ; Conference date: 28-03-2005 Through 29-03-2005",

}

TY - JOUR

T1 - Embedded fingerprint identification system based on DSP

AU - Xie, Weihua

AU - Tian, Jie

AU - Yang, Xin

AU - Chen, Hong

AU - He, Yuliang

AU - Zhang, Tanghui

PY - 2005

Y1 - 2005

N2 - Fingerprint recognition is implemented on Ti DSP chip Ti 5402. The algorithm is prompt and practicable. Enhance part adopts a fast orientation filter to improve inputting image quality combining fast orientation interpolation method. On the other hand, the orientation field is used in fingerprint image segment. Matching part uses point match method and combines some post-processing in order to get good match result. One fusion way is introduced in enrollment. In DSP implement phase, the system frame adopts one kind of dispatched system structure aiming at the 5402 features. Otherwise the algorithm of fingerprint recognition is modified and optimized based on DSP instructions. Experiment result indicates that system performance is good.

AB - Fingerprint recognition is implemented on Ti DSP chip Ti 5402. The algorithm is prompt and practicable. Enhance part adopts a fast orientation filter to improve inputting image quality combining fast orientation interpolation method. On the other hand, the orientation field is used in fingerprint image segment. Matching part uses point match method and combines some post-processing in order to get good match result. One fusion way is introduced in enrollment. In DSP implement phase, the system frame adopts one kind of dispatched system structure aiming at the 5402 features. Otherwise the algorithm of fingerprint recognition is modified and optimized based on DSP instructions. Experiment result indicates that system performance is good.

KW - DSP

KW - Embedded system

KW - Fingerprint identification

KW - Optimization

UR - https://www.scopus.com/pages/publications/26444558110

U2 - 10.1117/12.603234

DO - 10.1117/12.603234

M3 - 会议文章

AN - SCOPUS:26444558110

SN - 0277-786X

VL - 5779

SP - 363

EP - 372

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

M1 - 41

T2 - Biometric Technology for Human Identification II

Y2 - 28 March 2005 through 29 March 2005

ER -

Embedded fingerprint identification system based on DSP

摘要

访问文件

其它文件与链接

指纹

引用此