摘要
利用虹膜图像中丰富的结构和纹理特征作为身份鉴别的依据,与其他生物特征识别相比,具有更高的可靠性.虹膜识别系统包括虹膜图像采集、虹膜图像预处理、特征提取、匹配与识别等部分.该文提出一种基于k-近邻分类器虹膜识别方法,该方法先对虹膜图像进行定位、归一化和增强等预处理,利用Gabor滤波实现虹膜纹理特征的提取,再用k-近邻分类器进行匹配,达到了识别的目的.实验结果表明,该方法是可行的.
The abundant structure and streak feature of iris image can be used as personal identification. This capacity is more reliable than other biometric characteristic recognition. A iris recognition system is based on four parts ： iris image sampling, iris image preprocessing, feature extraction, iris image matching and recognition. An iris recognition approach based on image Knn classifier is presented in this paper. The preprocessing includes location, normalization and enhancement. After that, the iris streak feature will be extracted by Gabor filter and the feature will be used in iris image matching by Knn classifier. Its results show that the method is feasible and prior to others.
出处
《湖南工程学院学报（自然科学版）》
2006年第3期5-8,共4页
Journal of Hunan Institute of Engineering(Natural Science Edition)
基金
国家自然科学基金(重点)项目(60234030)
国防科工委项目(A1420060159)
