Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (9): 164-167.DOI: 10.3778/j.issn.1002-8331.2009.09.047

• 图形、图像、模式识别 • Previous Articles     Next Articles

Research on fingerprint image quality automatic measures

LIU Lian-hua,TAN Tai-zhe   

  1. Faculty of Computer,Guangdong University of Technology,Guangzhou 510006,China
  • Received:2008-09-19 Revised:2008-11-19 Online:2009-03-21 Published:2009-03-21
  • Contact: LIU Lian-hua

指纹图像质量自动评测方法研究

刘莲花,谭台哲   

  1. 广东工业大学 计算机学院,广州 510006
  • 通讯作者: 刘莲花

Abstract: Accurate minutiae extraction from fingerprint images is heavily dependent on the quality of the fingerprint image.In order to improve the performance of the system,it is necessary to measure the quality of the captured fingerprint images.This paper presents a novel method for fingerprint image quality.Five features are extracted from the fingerprint image to analyze the quality and the feature vector is defined as being formed from the five features.Then an SVM classifier,which can solve small-sample learning problems with good generalization,is trained to classify the fingerprint image.The fingerprint image is separated into one of the three classes,good-quality,medium-quality,or poor-quality.Experimental results on FVC2004 and the private database show that the proposed method is an effective and efficient scheme to measure the quality of the fingerprint image.

Key words: fingerprint image quality, automatic measure, feature vector, Support Vector Machine classifier

摘要: 要准确地从指纹图像中提取细节点,在很大程度上依赖于所采集的指纹图像的质量。为了提高指纹识别系统的性能,必须对输入到系统的指纹图像进行质量的自动评测。提出一种新的方法,先从指纹图像提取5个评测参数,组成质量评测向量,再采用小样本情况下具有分类优势的支持向量机(SVM)对指纹图像进行分类,将指纹图像分为好、中、差三类。实验表明,提出的方法能有效地进行指纹图像质量自动评测。

关键词: 指纹图像质量, 自动评测, 特征向量, 支持向量机分类器