期刊
ELECTRONICS
卷 11, 期 20, 页码 -出版社
MDPI
DOI: 10.3390/electronics11203300
关键词
CNN; deep residual descriptors; sparse coding; vein recognition
资金
- Natural Science Foundation of the Jiangsu Higher Education Institutions of China [20KJB510051]
- Sichuan Science and Technology Program [2022YFG0032]
Vein recognition has gained attention due to its high security and reliability. Traditional vein recognition systems have issues such as uneven illumination, low contrast, and high inter-class similarities. Convolutional neural networks (CNNs) have been successful in large-scale image recognition tasks, motivating the use of CNNs to design a robust and discriminative vein recognition system.
Vein recognition has been drawing more attention recently because it is highly secure and reliable for practical biometric applications. However, underlying issues such as uneven illumination, low contrast, and sparse patterns with high inter-class similarities make the traditional vein recognition systems based on hand-engineered features unreliable. Recent successes of convolutional neural networks (CNNs) for large-scale image recognition tasks motivate us to replace the traditional hand-engineered features with the superior CNN to design a robust and discriminative vein recognition system. To address the difficulty of direct training or fine-tuning of a CNN with existing small-scale vein databases, a new knowledge transfer approach is formulated using pre-trained CNN models together with a training dataset (e.g., ImageNet) as a robust descriptor generation machine. With the generated deep residual descriptors, a very discriminative model, namely deep residual vector encoding (DRVE), is proposed by a hierarchical design of dictionary learning, coding, and classifier training procedures. Rigorous experiments are conducted with a high-quality hand-dorsa vein database, and superior recognition results compared with state-of-the-art models fully demonstrate the effectiveness of the proposed models. An additional experiment with the PolyU multispectral palmprint database is designed to illustrate the generalization ability.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据