Iris recognition based on score level fusion by using SVM
Iris recognition based on score level fusion by using SVM
复制标题
DOI：
10.1016/j.patrec.2007.05.017
复制
发表时间：
2007-11-01
影响因子：
5.1
通讯作者：
Park, Kang Ryoung
中科院分区：
文献类型：
--
作者：
Park, Hyun-Ae;Park, Kang Ryoung
在传统的虹膜识别方法中，由于很难选择一个最优的小波滤波器来提取虹膜特征，所以采用了多个不同频率和核大小的小波滤波器。然而，这会导致处理时间和提取的特征大小增加。为了克服这一问题，人们提出了对提取的虹膜特征进行特征级融合，但这种方法需要一个复杂的降维过程。因此，我们提出了一种新的基于分数级融合的虹膜识别方法，该方法使用了两个Gabor小波滤波器和支持向量机。对于分数级融合，我们使用了Gabor滤波器产生的典型HD(Hamming Distance)，该方法可以很容易地应用于传统的虹膜识别系统。首先，在生成虹膜特征编码时，剔除了检测到的眼皮、睫毛和镜面反射区域作为虹膜特征提取中的噪声因素。其次，在登记时，我们检查了不是从眼皮、睫毛和SR遮挡区域生成的可靠虹膜特征代码的数量。只有当可靠码数超过预定阈值时，我们才以高置信度进行注册，从而降低了FRR(错误拒绝率)。第三，对局部和全局虹膜纹理分别使用两个Gabor滤波器，并利用支持向量机对这两个Gabor滤波器计算的HDs进行融合，大大降低了认证误差，实验结果表明，该方法的认证误差远小于单一Gabor滤波器、滤波器组、分数级和决策级融合方法的认证误差。(C)2007 Elsevier B.V.保留所有权利。
In conventional iris recognition methods, due to the difficulty of selecting one optimal wavelet filter for iris feature extraction, multiple wavelet filters (with different frequencies and kernel sizes) are adopted. However, this causes the processing time and the extracted feature size to increase. To overcome this problem, feature level fusion of the extracted iris features has been proposed, but this method requires a complicated dimension reduction procedure. Therefore, we propose a new iris recognition method based on score level fusion, using two Gabor wavelet filters and SVM (support vector machine). For score level fusion, we used the typical HD (Hamming distance) produced by a Gabor filter, which can easily be applied to conventional iris recognition systems.The proposed method has three novelties compared to previous works. First, when generating iris feature codes, we excluded detected eyelid, eyelash and SR (specular reflection) regions, which act as noise factors in iris feature extraction. Second, for enrollment, we checked the number of reliable iris feature codes that were not generated from the eyelid, eyelash and SR occluded regions. Only if the number of reliable codes exceeded in the predetermined threshold, we performed enrollment with high confidence, which reduced the FRR (false rejection rate). Third, two Gabor filters were used for local and global iris textures and the HDs calculated by those Gabor filters were fused by the SVM and the consequent authentication error was greatly reduced.Experimental results showed that the authentication error of the proposed method was much smaller than the authentication errors when using the single Gabor filter, the filter-bank, the score level and the decision level fusion methods. (C) 2007 Elsevier B.V. All rights reserved.