Deep Representation for Finger-Vein Image-Quality Assessment
Deep Representation for Finger-Vein Image-Quality Assessment
复制标题
DOI：
10.1109/tcsvt.2017.2684826
复制
发表时间：
2018-08-01
影响因子：
8.4
通讯作者：
El-Yacoubi, Mounim A.
中科院分区：
文献类型：
--
作者：
Qin, Huafeng;El-Yacoubi, Mounim A.
手指静脉生物识别技术已经被广泛研究用于个人认证。手指静脉验证中的一个公开问题是缺乏对图像质量退化的鲁棒性。质量差的图像中的伪特征和缺失特征可能会降低系统的性能。尽管指静脉质量评估的最新进展，目前的解决方案依赖于领域知识。在本文中，我们提出了一种用于表示学习的深度神经网络（DNN），以使用非常有限的知识来预测图像质量。由生物特征质量评估的主要目标驱动，即，为了验证误差最小化，我们假设低质量图像在验证系统中被错误地拒绝。基于这一假设，低质量和高质量的图像被自动标记。然后，我们在得到的数据集上训练DNN来预测图像质量。为了进一步提高DNN的鲁棒性，将手指静脉图像划分为各种块，在其上训练基于块的DNN。最深的层与补丁一起形成一个互补的和过完备的表示。随后，从测试图像中的每个补丁的质量估计和图像补丁的质量分数联合输入到概率支持向量机（P-SVM），以提高质量评估性能。据我们所知，这是首次提出的基于深度学习的质量评估工作，不仅适用于指静脉生物识别，而且适用于其他生物识别。在两个公共手指静脉数据库上的实验结果表明，该方法能够准确识别高质量和低质量图像，在降低等误率方面明显优于现有方法。
Finger-vein biometrics has been extensively investigated for personal authentication. One of the open issues in finger-vein verification is the lack of robustness against image-quality degradation. Spurious and missing features in poor-quality images may degrade the system's performance. Despite recent advances in finger-vein quality assessment, current solutions depend on domain knowledge. In this paper, we propose a deep neural network (DNN) for representation learning to predict image quality using very limited knowledge. Driven by the primary target of biometric quality assessment, i.e., verification error minimization, we assume that low-quality images are falsely rejected in a verification system. Based on this assumption, the low-and high-quality images are labeled automatically. We then train a DNN on the resulting data set to predict the image quality. To further improve the DNN's robustness, the finger-vein image is divided into various patches, on which a patch-based DNN is trained. The deepest layers associated with the patches form together a complementary and an over-complete representation. Subsequently, the quality of each patch from a testing image is estimated and the quality scores from the image patches are conjointly input to probabilistic support vector machines (P-SVM) to boost quality-assessment performance. To the best of our knowledge, this is the first proposed work of deep learning-based quality assessment, not only for finger-vein biometrics, but also for other biometrics in general. The experimental results on two public finger-vein databases show that the proposed scheme accurately identifies high-and low-quality images and significantly outperforms existing approaches in terms of the impact on equal error-rate decrease.