Deep Contactless Fingerprint Unwarping
Deep Contactless Fingerprint Unwarping
复制标题
DOI：
10.1109/icb45273.2019.8987292
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Ali Dabouei;Sobhan Soleymani;J. Dawson;N. Nasrabadi
中科院分区：
文献类型：
--
作者：
Ali Dabouei;Sobhan Soleymani;J. Dawson;N. Nasrabadi
非接触式指纹已经成为一种方便、廉价和卫生的采集指纹样本的方法。然而，由于两种模式之间的弹性和透视失真，将非接触式指纹与传统的接触式指纹进行交叉匹配是一项具有挑战性的任务。现有的交叉匹配方法只对接触式指纹样本的弹性变形进行校正，以减少几何失配，而忽略了非接触式指纹的透视变形。采用经典的变形校正技术来补偿透视失真需要大量的细节点注释的非接触式指纹。然而，非接触式样本的细节点标注是一项劳动强度大且不准确的任务，特别是对于透视投影严重失真的区域。在这项研究中，我们提出了一种结合矫正和脊线增强网络的深度模型来矫正非接触式指纹的透视失真。脊线增强网络为训练校正网络提供了间接监督，并消除了对估计的翘曲参数的地面真值的需要。使用两个公开的非接触指纹数据集进行的综合实验表明，所提出的去扭曲方法平均导致从非接触指纹中检测到的细节点数量增加了17%。因此，在具有挑战性的2D/3D指纹数据集上，该模型获得了7.71%的等错误率和61.01%的Rank-1准确率。
Contactless fingerprints have emerged as a convenient, inexpensive, and hygienic way of capturing fingerprint samples. However, cross-matching contactless fingerprints to the legacy contact-based fingerprints is a challenging task due to the elastic and perspective distortion between the two modalities. Current cross-matching methods merely rectify the elastic distortion of the contact-based samples to reduce the geometric mismatch and ignore the perspective distortion of contactless fingerprints. Adopting classical deformation correction techniques to compensate for the perspective distortion requires a large number of minutiae-annotated contactless fingerprints. However, annotating minutiae of contactless samples is a labor-intensive and inaccurate task especially for regions which are severely distorted by the perspective projection. In this study, we propose a deep model to rectify the perspective distortion of contactless fingerprints by combining a rectification and a ridge enhancement network. The ridge enhancement network provides indirect supervision for training the rectification network and removes the need for the ground truth values of the estimated warp parameters. Comprehensive experiments using two public datasets of contactless fingerprints show that the proposed unwarping approach, on average, results in a 17% increase in the number of detectable minutiae from contactless fingerprints. Consequently, the proposed model achieves the equal error rate of 7.71% and Rank-1 accuracy of 61.01% on the challenging dataset of ‘2D/3D’ fingerprints.