An approach to SWIR hyperspectral hand biometrics
An approach to SWIR hyperspectral hand biometrics
复制标题
DOI：
10.1016/j.ins.2013.10.011
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
M. A. Ferrer-Ballester;A. Morales;Alba Díaz
中科院分区：
文献类型：
--
作者：
M. A. Ferrer-Ballester;A. Morales;Alba Díaz
基于手的生物统计学包括一些最有用的个人身份识别技术。寻找新的技术，补充现有的方法，是一个开放的主题。本文探讨了实用的高光谱图像的手识别。高光谱技术允许感测皮下组织结构，这是显着不同的人。使用SWIR相机结合光学光谱仪收集数据。这将相机转换成一个线扫描高光谱成像设备。三个特征提取方法的高光谱手曲线表征进行了研究。它们基于自动选择的不同空间手位置处的面积、斜率或曲率。我们报告了一组实验，探讨：最好的手区提取局部高光谱特征，对训练样本的数量的鲁棒性，错误检测和遮挡。不同的策略相结合的光谱特征与几何性状可在高光谱立方体进行了讨论。我们的实验表明，人体组织的局部光谱特性是有效的生物特征识别的性能接近或优于其他手的特征所获得的判别。从154人的数据库中获得了0.05%的等错误率和96.71%的识别率。这些结果沿着其较高的鲁棒性欺骗攻击的高光谱特征的人识别的一个有前途的选择。
Hand based biometry includes some of the most useful technologies for person identification. The search for new techniques, which complement the battery of existing methods, is an open topic. This paper examines the utility of hyperspectral imagery for hand recognition. Hyperspectral technology permits the sensing of the subsurface tissue structure, which is significantly different from person to person. The data are collected using a SWIR camera in conjunction with an optical spectrograph. This transforms the camera into a line-scan hyperspectral imaging device.Three feature extraction methods for hyperspectral hand curve characterization are examined. They are based on the area, slope or curvature at different automatically selected spatial hand positions. We report a set of experiments which explore: best hand zones for extracting local hyperspectral features; robustness against the number of training samples; error detection; and occlusion. Different strategies for combining the spectral features with geometric traits available in the hyperspectral cube are discussed. Our experiments show that local spectral properties of human tissue are effective discriminants for biometric recognition with a performance near to or better than that obtained by other hand traits. Equal Error Rates of 0.05% and an identification rate of 96.71% are obtained from a database of 154 people. These results along with their higher robustness to spoofing attacks make the hyperspectral features a promising alternative for person identification.