摘要： 针对虹膜识别中存在的问题，在识别时应该尽可能将虹膜有效信息提取出来，而将眼皮、睫毛、光点的反射等去除，同时在特征提取中，提出了通过噪声扩展方法消除噪声信号在编码过程中带来的影响。实验结果表明该文提出的方法有助于提高识别的可靠性和模式分类能力。

关键词: 虹膜识别；噪声检测；模板匹配；汉明距离

Abstract: This paper detects iris effective information and noises with high accuracy.The noise affection in iris encoding is avoided by noise-expanded approach at the same time. Experimental results show that the approach is helpful to improve pattern classification effect and recognition reliability.

Key words: Iris recognition; Noise detecting; Template matching; Hamming distance