Minutia Cylinder Code-based Fingerprint Matching Optimization using GPU

被引:0
作者
Sutarno, Muhamad Visat [1 ]
Kistijantoro, Achmad Imam [1 ]
机构
[1] Inst Teknol Bandung, Sch Elect Engn & Informat, Bandung, Indonesia
来源
PROCEEDINGS OF 2017 INTERNATIONAL CONFERENCE ON DATA AND SOFTWARE ENGINEERING (ICODSE) | 2017年
关键词
CUDA; fingerprint matching; GPU; MCC; parallel; optimization;
D O I
暂无
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
The advancement of technology has been giving contributions to the rapid growth of the use of digital data. In this digital era, lots of physical data have been transformed into the digital ones. One example of the use of digital data is the digital biometric fingerprint data on the Electronic Identity Card (KTP-el). Fingerprint matching can take a long time to process if the data is large enough. Thus, there is a need for a parallel fingerprint matching. Based on this rationale, this paper aims to improve the fingerprint matching performance, in the current state of the art linear solution, by using the Minutia Cylinder-Code (MCC) algorithm in parallel on GPU. Based on the experiment and testing, the proposed solution has a significantly better run time compared to the state of the art linear solution while maintaining the accuracy.
引用
收藏
页数:5
相关论文
共 9 条
  • [1] [Anonymous], IEEE T PATTERN ANAL
  • [2] [Anonymous], 2003, Handbook of fingerprint recognition
  • [3] [Anonymous], MIN CYL COD SDK
  • [4] Gutierrez P. D., 2013, IEEE T INFORM FORENS
  • [5] Maio D., 2004, BIOMETRIC AUTHENTICA
  • [6] NVIDIA, CUDA C++ Programming Guide
  • [7] NVIDIA, WHAT IS GPU ACC COMP
  • [8] Statistik Badan Pusat, 2010, SENS PRND 2010 IND
  • [9] Watson Craig I, 2016, TECH REP