Premium
Fast approximation of Parzen density estimation for fingerprint alignment
Author(s) -
Park Heemin
Publication year - 2012
Publication title -
ieej transactions on electrical and electronic engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.254
H-Index - 30
eISSN - 1931-4981
pISSN - 1931-4973
DOI - 10.1002/tee.21822
Subject(s) - kernel density estimation , fingerprint (computing) , outlier , density estimation , noise (video) , computer science , artificial intelligence , pattern recognition (psychology) , probability density function , algorithm , mathematics , statistics , image (mathematics) , estimator
Previous fingerprint alignment approaches may produce biased results because of outliers caused by fingerprint noise. To account for noise, major trends from transformations can be extracted using Parzen density estimation. However, this extraction is computationally intense. Here, we propose a fast approximation algorithm of the Parzen density estimation for global fingerprint alignment. Experimental results show that the proposed algorithm's performance is as good as that of Parzen density estimation and it has a much shorter execution time. © 2012 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.