基于2D-Gabor滤波器的虹膜噪声检测方法

人眼在自然张开状态下，虹膜区域会受到部分眼睑、睫毛的遮挡，这些噪声会降低虹膜识别的准确性，因而在识别时应该尽可能将虹膜有效信息提取出来，而将眼睑、睫毛等干扰去除。为此本文提出了一种在归一化后的虹膜图像上利用2D-Gabor滤波器检测和去除虹膜区域内噪声的方法，并将噪声区域标记。在虹膜匹配时，通过将虹膜代码中的干扰位去除来尽量避免噪声对于虹膜识别的影响。实验结果表明本文提出的方法可以准确检测并标记噪声区域，有助于提高识别的可靠性和识别准确率。

Noise Detection Method of Iris by Using the 2D-Gabor Filter

In the normal open situation, some parts of the iris may be blocked by the eyelid or eyelash. The noise will degrade the accuracy of the iris recognition. Therefore, the best way is using the effective information without the noise in the iris recognition. So a noise detection method by using the 2D-Gabor filter is proposed. To avoid the influence of the noise, the bits of the code which is in the noise area are taken out during matching. The results of experiments prove that this method can detect and mark the noise area exactly, and improve the reliability and accuracy of iris recognition.