A fourier transform quality measure for iris images

2014 International Symposium on Biometrics and Security Technologies (ISBAST) Pub Date : 2014-08-01 DOI:10.1109/ISBAST.2014.7013093

Sisanda Makinana, J. V. D. Merwe, T. Malumedzha

引用次数: 3

Abstract

Iris recognition systems have attracted much attention for their uniqueness, stability and reliability. However, performance of this system depends on quality of acquired iris sample. This is because in order to obtain reliable features good quality images are to be used. Thus, it is important to accurately assess image quality before applying feature extraction algorithm in order to avoid insufficient results. This study aims to quantitatively analyse the effect of iris image quality in order to ensure that good quality images are selected for feature extraction, in order to improve iris recognition system. In addition, this research proposes a measure of iris image quality using a Fourier Transform. The experimental results demonstrate that the proposed algorithm shows better performance in quality classification as it yields a 97% accuracy rate than the existing algorithms.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

虹膜图像的傅里叶变换质量度量

虹膜识别系统以其独特性、稳定性和可靠性而备受关注。然而，该系统的性能取决于虹膜样本的质量。这是因为为了获得可靠的特征，需要使用高质量的图像。因此，在应用特征提取算法之前，准确地评估图像质量，以避免结果不充分是非常重要的。本研究旨在定量分析虹膜图像质量的影响，以确保选择高质量的图像进行特征提取，从而改进虹膜识别系统。此外，本研究提出了使用傅里叶变换测量虹膜图像质量的方法。实验结果表明，该算法在质量分类方面具有更好的性能，准确率达到97%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

2014 International Symposium on Biometrics and Security Technologies (ISBAST)

自引率

0.00%

发文量

期刊最新文献

Improved skin detection based on dynamic threshold using multi-colour space Signature-Based Anomaly intrusion detection using Integrated data mining classifiers Distributed Denial of Service detection using hybrid machine learning technique Survey of anti-phishing tools with detection capabilities Effective mining on large databases for intrusion detection