[论文解读] Cross-Sensor Periocular Biometrics: A Comparative Benchmark including Smartphone Authentication

Fernando Alonso‐Fernandez, Kiran Raja+5 more|arXiv (Cornell University)|Feb 21, 2019

Biometric Identification and Security参考文献 71被引用 8

一句话总结

本文提出一种基于线性逻辑回归的多算法融合方法，用于提升可见光（VW）与近红外（NIR）光谱之间的跨传感器眼周识别性能，实现EER为0.22%、FAR=0.01%时FRR为0.62%，在第一届跨光谱虹膜/眼周识别竞赛中表现最佳。

ABSTRACT

The massive availability of cameras and personal devices results in a wide variability between imaging conditions, producing large intra-class variations and performance drop if such images are compared for person recognition. However, as biometric solutions are extensively deployed, it will be common to replace acquisition hardware as it is damaged or newer designs appear, or to exchange information between agencies or applications in heterogeneous environments. Furthermore, variations in imaging bands can also occur. For example, faces are typically acquired in the visible (VW) spectrum, while iris images are captured in the near-infrared (NIR) spectrum. However, cross-spectrum comparison may be needed if for example a face from a surveillance camera needs to be compared against a legacy iris database. Here, we propose a multialgorithmic approach to cope with cross-sensor periocular recognition. We integrate different systems using a fusion scheme based on linear logistic regression, in which fused scores tend to be log-likelihood ratios. This allows easy combination by just summing scores of available systems. We evaluate our approach in the context of the 1st Cross-Spectral Iris/Periocular Competition, whose aim was to compare person recognition approaches when periocular data from VW and NIR images is matched. The proposed fusion approach achieves reductions in error rates of up to 20-30% in cross-spectral NIR-VW comparison, leading to an EER of 0.22% and a FRR of just 0.62% for FAR=0.01%, representing the best overall approach of the mentioned competition.. Experiments are also reported with a database of VW images from two different smartphones, achieving even higher relative improvements in performance. We also discuss our approach from the point of view of template size and computation times, with the most computationally heavy system playing an important role in the results.

研究动机与目标

• 为解决成像设备间因跨传感器和跨光谱差异导致的眼周识别性能下降问题。
• 开发一种稳健的融合框架，整合多个生物特征系统以提升异质成像条件下的识别准确率。
• 在真实世界的跨光谱和跨设备场景中评估所提方法，包括基于智能手机的VW图像。
• 分析计算复杂度与模板大小对系统性能及融合效果的影响。

提出的方法

• 作者采用基于线性逻辑回归的多算法融合策略，整合多个眼周识别系统的得分。
• 融合得分被建模为对数似然比，实现不同系统得分的直接相加，无需重新校准。
• 该方法应用于模拟真实部署场景的可见光（VW）与近红外（NIR）眼周图像之间的跨光谱对比。
• 该方法在第一届跨光谱虹膜/眼周识别竞赛数据集上得到验证，涵盖跨光谱与跨设备（智能手机）评估。
• 融合框架设计为可扩展且高效，涵盖计算负载与模板大小的性能分析。
• 计算开销最大的系统在最终融合结果中贡献显著，凸显其在集成中的关键作用。

实验结果

研究问题

• RQ1 基于线性逻辑回归的多算法融合方法在降低跨传感器眼周识别错误率方面效果如何？
• RQ2 在眼周生物特征识别中，将可见光与近红外光谱的系统进行融合可实现多大性能提升？
• RQ3 当应用于不同智能手机设备在不同成像条件下拍摄的眼周图像时，该融合方法表现如何？
• RQ4 各独立系统对最终融合结果的相对贡献如何，尤其是在计算成本与准确率方面？
• RQ5 模板大小与计算时间如何影响融合系统的整体性能及实际部署？

主要发现

• 所提融合方法在跨光谱NIR-VW眼周识别中实现0.22%的等错误率（EER），为第一届跨光谱虹膜/眼周识别竞赛中的最佳结果。
• 与单一系统相比，该方法在跨光谱对比中错误率降低高达20-30%。
• 对于来自两台不同设备的智能手机可见光图像，融合带来的相对性能提升甚至高于跨光谱场景。
• 在FAR为0.01%时，错误拒绝率（FRR）降低至0.62%，表明在严格安全阈值下具有极强的可靠性。
• 计算最复杂的系统在融合结果中起关键作用，对最终性能提升有显著贡献。
• 通过将输出视为对数似然比，该融合框架实现了有效的得分组合，简化了在多样化生物特征系统间的集成。