Comparison of the Legendre, Zernike and Pseudo-Zernike Moments for Feature Extraction in Iris Recognition

2013 5th International Conference on Computational Intelligence and Communication Networks Pub Date : 2013-09-27 DOI:10.1109/CICN.2013.54

Seyed Jabbar Hosaini, S. Alirezaee, M. Ahmadi, S. Makki

引用次数: 13

Abstract

In this paper we compare the performance of Legendre moments, Zernike moments and Pseudo-Zernike moments in feature extraction for iris recognition. We have increased the moment orders until the best recognition rate is achieved. Robustness of these moments in various orders has been evaluated in presence of White Gaussian Noise. Numerical results indicate that recognition rate by the Legendre, Zernike and Pseudo-Zernike moments in higher orders are approximately identical. However, average computation time for feature extraction is 4.5, 18 and. 75 seconds respectively for the Legendre, Zernike and Pseudo-Zernike moments of order 14. On the other hand, the result indicates the Legendre moment is more robust than the others against the white Gaussian noise.

查看原文本刊更多论文

虹膜识别中特征提取的Legendre、Zernike和Pseudo-Zernike矩的比较

本文比较了Legendre矩、Zernike矩和Pseudo-Zernike矩在虹膜识别特征提取中的性能。我们不断增加矩阶，直到达到最佳识别率。在存在高斯白噪声的情况下，对这些矩在不同阶次的鲁棒性进行了评估。数值结果表明，高阶的Legendre、Zernike和Pseudo-Zernike矩的识别率近似相同。然而，特征提取的平均计算时间分别为4.5、18和18。14阶的Legendre、Zernike和Pseudo-Zernike力矩分别为75秒。另一方面，结果表明，勒让德矩对高斯白噪声的鲁棒性优于其他矩。

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分钟内获得全文求助全文

来源期刊

2013 5th International Conference on Computational Intelligence and Communication Networks

自引率

0.00%

发文量