首页|使用动态数据增强和对比学习进行虹膜验证

使用动态数据增强和对比学习进行虹膜验证

扫码查看
原文链接
  • 万方数据
  • 维普
虹膜验证因其独特性、 稳定性和非侵入性而受到广泛关注.深度学习技术在虹膜验证领域取得了重要的进展,通过使用卷积神经网络(Convolutional neural network,CNN),可以自动提取和学习虹膜图像的特征,实现高精度的身份验证.然而,类内变异性和有限的数据规模等挑战可能会影响验证准确性.为了解决这些问题,我们提出了一种基于动态数据增强和对比学习的虹膜验证方法.设计了四种数据增强策略,用于在线虹膜增强和数据集扩展,通过使用数据增强概率调度器(Data augmentation probability scheduler,DAPS),进一步提高了虹膜验证的准确性.采用MobileNetV3作为骨干网络,并通过对比学习对其进行优化,用于处理3通道的虹膜对.提出的方法在两个基准虹膜数据库,CASIA-V4-Interval和CASIA-V4-Thousand上进行了评估,准确性分别达到了99.85％和98.82％.实验结果表明,在训练样本数量较少的情况下,该方法可获得具有竞争性的性能.
Using dynamic data augmentation and contrastive learning for iris verification
Iris verification has gained extensive attention because of its uniqueness, stability, and non-invasiveness. Deep learning techniques have made significant progress in the field of iris verification. By using convolutional neural networks (CNNs), features of iris images can be automatically extracted and learned, enabling high-precision identity verification. However, challenges such as intra-class variability and limited dataset size can compromise verification accuracy. To address these issues, we proposed an iris verification method based on dynamic data augmentation and contrastive learning. Four data augmentation strategies were carefully designed for online iris enhancement and dataset expansion, and the accuracy of iris verification was further improved by using data augmentation probability scheduler(DAPS). The MobileNetV3 was employed as the backbone network, which was optimized with contrastive learning for 3-channel iris pairs. The proposed method was evaluated on two benchmark iris databases, CASIA-V4-Interval and CASIA-V4-Thousand, achieving high accuracies of 99.85％ and 98.82％, respectively. Experimental results demonstrate that the proposed method can achieve competitive performance with a small number of training samples.

iris verificationcontrastive learningconvolutional neural network (CNN)data augmentation

贺兰迪、纪德赞、董兴辰、苏明鑫、周卫东

展开 >

山东大学微电子学院,山东济南 250101

虹膜验证 对比学习 卷积神经网络 数据增强

National Natural Science Foundation of ChinaKey Program of the Natural Science Foundation of Shandong Province

62271291ZR2020LZH009

2024

10.62756/jmsi.1674-8042.2024006

测试科学与仪器
中北大学

测试科学与仪器

影响因子：0.111
ISSN：1674-8042
年,卷(期)：2024.15(1)
  • 34