[论文解读] A New Periocular Dataset Collected by Mobile Devices in Unconstrained Scenarios
本论文介绍了UFPR-Periocular数据集,该数据集是目前公开可用的规模最大、在非受限条件下采集的虹膜周围区域数据集,包含1,122名受试者和196部移动设备,共三个会话。基于MobileNetV2的多任务深度学习模型在封闭世界协议下实现了84.32%的rank-1识别率和0.81%的EER,表明在真实世界可变性条件下,基于移动设备的虹膜周围识别仍需进一步研究。
Recently, ocular biometrics in unconstrained environments using images obtained at visible wavelength have gained the researchers' attention, especially with images captured by mobile devices. Periocular recognition has been demonstrated to be an alternative when the iris trait is not available due to occlusions or low image resolution. However, the periocular trait does not have the high uniqueness presented in the iris trait. Thus, the use of datasets containing many subjects is essential to assess biometric systems' capacity to extract discriminating information from the periocular region. Also, to address the within-class variability caused by lighting and attributes in the periocular region, it is of paramount importance to use datasets with images of the same subject captured in distinct sessions. As the datasets available in the literature do not present all these factors, in this work, we present a new periocular dataset containing samples from 1,122 subjects, acquired in 3 sessions by 196 different mobile devices. The images were captured under unconstrained environments with just a single instruction to the participants: to place their eyes on a region of interest. We also performed an extensive benchmark with several Convolutional Neural Network (CNN) architectures and models that have been employed in state-of-the-art approaches based on Multi-class Classification, Multitask Learning, Pairwise Filters Network, and Siamese Network. The results achieved in the closed- and open-world protocol, considering the identification and verification tasks, show that this area still needs research and development.
研究动机与目标
- 解决在非受限条件下,通过移动设备采集的大规模真实世界虹膜周围数据集的缺乏问题。
- 评估最先进深度学习模型在因光照、姿态和设备差异导致高类内可变性情况下的虹膜周围识别性能。
- 研究多任务学习在提升识别与验证任务中判别性特征提取方面的效果。
- 为未来移动眼生物识别研究提供基准数据集和实验设置。
提出的方法
- 在非受限环境中,使用196部不同移动设备,从1,122名受试者中采集了33,660张虹膜周围图像,共三个会话。
- 人工标注了眼角位置,并为每张图像提供了包括年龄范围、性别和设备型号在内的元数据。
- 训练并评估了多种CNN架构,包括多分类模型、多任务学习模型、Siamese网络和成对滤波网络。
- 采用封闭世界和开放世界协议评估识别与验证性能。
- 通过消融研究评估多任务学习框架中各项任务的贡献。
- 使用数据增强和属性归一化技术,减轻光照、模糊、遮挡和眼镜等因素引起的误差。
实验结果
研究问题
- RQ1在非受限移动场景下,虹膜周围识别模型的性能如何随不同深度学习架构而变化?
- RQ2辅助任务(如性别、年龄、设备型号)对提升虹膜周围特征判别能力的相对贡献是什么?
- RQ3光照、遮挡和图像分辨率如何影响真实世界移动虹膜周围识别中的验证准确率?
- RQ4多任务学习能否有效降低类内可变性并提升基于移动设备的虹膜周围识别的泛化能力?
- RQ5在真实世界虹膜周围识别中,封闭世界与开放世界协议之间的性能差距是多少?
主要发现
- UFPR-Periocular数据集在可见光谱虹膜周围识别领域中,是受试者数量(1,122名)和独特移动设备数量(196部)最多的公开数据集。
- 基于MobileNetV2的多任务学习模型表现最佳,在封闭世界协议下实现了84.32%的rank-1识别率和0.81%的等错误率(EER)。
- 在开放世界协议下,同一模型在阈值为0.80和0.78时,EER达到2.81%,表明对未知受试者具有良好的鲁棒性。
- 消融研究显示,设备型号识别任务影响最大,其次是年龄范围、性别和眼睛侧分类。
- 主观分析表明,光照、遮挡和低图像分辨率是导致误验证决策的主要原因。
- 尽管性能表现良好,但结果表明移动虹膜周围识别在开放世界和真实世界条件下仍需显著改进。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。