Iris Recognition using Robust Localization and Nonsubsampled Contourlet Based Features
Iris Recognition using Robust Localization and Nonsubsampled Contourlet Based Features
复制标题
DOI：
10.1007/s11265-014-0911-2
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
S. Khalighi;Fatemeh Pak;Parisa Tirdad;U. Nunes
中科院分区：
文献类型：
--
作者：
S. Khalighi;Fatemeh Pak;Parisa Tirdad;U. Nunes
传统的虹膜识别方法对于眼睛图像可能包含非理想数据（如镜面反射、偏离角度视图、眼睑、睫毛和其他伪影）的数据集表现不佳。本文利用一种新的时频和空域尺度、位移和旋转不变特征提取方法，为可靠的虹膜识别方法做出了贡献。实际上，在归一化虹膜图像上应用2级非下采样contourlet变换（NSCT），并在空间图像和NSCT频率子带上计算3个不同方向的灰度共生矩阵（GLCM）。此外，通过执行虹膜定位算法和四个感兴趣区域（ROI）选择来降低被遮挡部分的影响。对提取的特征集进行变换和归一化，以减少特征向量极值的影响。接下来，采用过滤阶段和基于包装的选择两步方法选择虹膜识别的重要特征。最后，使用支持向量机（SVM）对选择的特征集进行分类。本文提出的虹膜识别方法在公共虹膜数据集CASIA Ver.1和CASIA ver .4 lamp上进行了测试，显示了最先进的性能。
The conventional iris recognition methods do not perform well for the datasets where the eye image may contain nonideal data such as specular reflection, off-angle view, eyelid, eyelashes and other artifacts. This paper gives contributions for a reliable iris recognition method using a new scale-, shift- and rotation-invariant feature-extraction method in time-frequency and spatial domains. Indeed, a 2-level nonsubsampled contourlet transform (NSCT) is applied on the normalized iris images and a gray level co-occurrence matrix (GLCM) with 3 different orientations is computed on both spatial image and NSCT frequency subbands. Moreover, the effect of the occluded parts is reduced by performing an iris localization algorithm followed by a four regions of interest (ROI) selection. The extracted feature set is transformed and normalized to reduce the effect of extreme values in the feature vector. Next, significant features for iris recognition are selected by a two-step method composed by a filtering stage and wrapper based selection. Finally, the selected feature set is classified using support vector machine (SVM). The proposed iris identification method was tested on the public iris datasets CASIA Ver.1 and CASIA Ver.4-lamp showing a state-of-the-art performance.