Towards open-set touchless palmprint recognition via weight-based meta metric learning.
Towards open-set touchless palmprint recognition via weight-based meta metric learning.
复制标题
DOI：
10.1016/j.patcog.2021.108247
复制
发表时间：
2022-01
影响因子：
8
通讯作者：
Zhong D
中科院分区：
文献类型：
--
作者：
Shao H;Zhong D
在新型冠状病毒2019 （COVID-19）之后，非接触式生物识别技术变得重要起来。考虑到COVID-19期间的卫生问题，非接触式掌纹识别因其便利性、用户友好性和高准确性而显示出巨大的潜力。然而，以往的掌纹识别方法主要集中在近距离场景。本文提出了一种新的基于权重的元度量学习（W2ML）方法，用于精确的开集非接触式掌纹识别，该方法在训练过程中只看到部分类别。采用元方法学习基于深度度量学习的特征提取器，提高了泛化能力。随机抽取多个集合来定义支持集和查询集，这些集合再组合成元集来约束基于集合的距离。特别是采用硬样本挖掘和加权来选择信息元集，提高了效率。最后，获得具有明显类间和类内差异的嵌入作为掌纹识别和验证的特征。在四个掌纹基准上进行了实验，包括14个有约束和无约束掌纹数据集。结果表明，W2ML方法在处理开放集掌纹识别问题上比现有方法具有更高的鲁棒性和效率，准确率提高了9.11%，平均错误率（EER）降低了2.97%。
Touchless biometrics has become significant in the wake of novel coronavirus 2019 (COVID-19). Due to the convenience, user-friendly, and high-accuracy, touchless palmprint recognition shows great potential when the hygiene issues are considered during COVID-19. However, previous palmprint recognition methods are mainly focused on close-set scenario. In this paper, a novel Weight-based Meta Metric Learning (W2ML) method is proposed for accurate open-set touchless palmprint recognition, where only a part of categories is seen during training. Deep metric learning-based feature extractor is learned in a meta way to improve the generalization ability. Multiple sets are sampled randomly to define support and query sets, which are further combined into meta sets to constrain the set-based distances. Particularly, hard sample mining and weighting are adopted to select informative meta sets to improve the efficiency. Finally, embeddings with obvious inter-class and intra-class differences are obtained as features for palmprint identification and verification. Experiments are conducted on four palmprint benchmarks including fourteen constrained and unconstrained palmprint datasets. The results show that our W2ML method is more robust and efficient in dealing with open-set palmprint recognition issue as compared to the state-of-the-arts, where the accuracy is increased by up to 9.11% and the Equal Error Rate (EER) is decreased by up to 2.97%.
登录
查看更多内容
影响因子：
3.9
作者：
Iovane, Gerardo;Bisogni, Carmen;Nappi, Michele
通讯作者：
Nappi, Michele
影响因子：
5.1
作者：
Guo, Zhenhua;Zhang, David;Zuo, Wangmeng
通讯作者：
Zuo, Wangmeng
用于掌纹表示和识别的局部判别方向二进制模式
DOI：
10.1109/tcsvt.2019.2890835
发表时间：
2020-02-01
影响因子：
8.4
作者：
Fei, Lunke;Zhang, Bob;Wen, Jie
通讯作者：
Wen, Jie
DOI：
10.1109/tsmcc.2010.2089516
发表时间：
2011-09-01
期刊：
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS
影响因子：
--
作者：
Kumar, Ajay;Shekhar, Sumit
通讯作者：
Shekhar, Sumit
用于掌纹识别的局部表观和潜在方向提取
影响因子：
8.1
作者：
Fei, Lunke;Zhang, Bob;Teng, Shaohua
通讯作者：
Teng, Shaohua