一种多特征提取及融合的虹膜识别方法

An Iris Recognition Algorithm of Multiple Features Extraction and Fusion

经典虹膜识别算法只提取单一的虹膜特征,提出一种采用多种特征提取及融合的虹膜识别算法.该算法首先对采集到的虹膜图像进行预处理,然后分别采用Log-Gabor滤波和Haar小波对预处理后图像进行特征提取,并用Hamming距离和加权欧式距离计算得到两个相似度,通过支持向量机(support vector machine,SVM)对相似度进行融合,得到匹配结果.实验证明,该算法有效,并能取得较高的识别率.

In this paper,an iris recognition method of multiple features extraction and fusion was proposed,which was different from the classical iris recognition methods that focused on a single texture feature. Firstly,the collected iris images were preprocessed. Secondly,features of the iris were extracted by using Log-Gabor filter and Haar wavelet respectively,and two similarity values were calculated by adopting Hamming Distance and Weighted Euclidean Distance. Finally,the Support Vector Machine was used to fuse the values of similarity and classify. The experimental results verified that the proposed method is effective and a higher recognition rate was achieved.