AlShehri Helala, Hussain Muhammad, AboAlSamh Hatim, AlZuair Mansour
College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia.
Sensors (Basel). 2018 Mar 28;18(4):1008. doi: 10.3390/s18041008.
The fingerprint is a commonly used biometric modality that is widely employed for authentication by law enforcement agencies and commercial applications. The designs of existing fingerprint matching methods are based on the hypothesis that the same sensor is used to capture fingerprints during enrollment and verification. Advances in fingerprint sensor technology have raised the question about the usability of current methods when different sensors are employed for enrollment and verification; this is a fingerprint sensor interoperability problem. To provide insight into this problem and assess the status of state-of-the-art matching methods to tackle this problem, we first analyze the characteristics of fingerprints captured with different sensors, which makes cross-sensor matching a challenging problem. We demonstrate the importance of fingerprint enhancement methods for cross-sensor matching. Finally, we conduct a comparative study of state-of-the-art fingerprint recognition methods and provide insight into their abilities to address this problem. We performed experiments using a public database (FingerPass) that contains nine datasets captured with different sensors. We analyzed the effects of different sensors and found that cross-sensor matching performance deteriorates when different sensors are used for enrollment and verification. In view of our analysis, we propose future research directions for this problem.
指纹是一种常用的生物识别方式，被执法机构和商业应用广泛用于身份验证。现有指纹匹配方法的设计基于这样一种假设：在注册和验证过程中使用相同的传感器来采集指纹。指纹传感器技术的进步引发了一个问题，即当在注册和验证时使用不同的传感器时，当前方法的可用性如何；这就是指纹传感器互操作性问题。为了深入了解这个问题并评估解决该问题的最先进匹配方法的现状，我们首先分析用不同传感器采集的指纹的特征，这使得跨传感器匹配成为一个具有挑战性的问题。我们证明了指纹增强方法对于跨传感器匹配的重要性。最后，我们对最先进的指纹识别方法进行了比较研究，并深入了解它们解决这个问题的能力。我们使用一个公共数据库（FingerPass）进行了实验，该数据库包含九个用不同传感器采集的数据集。我们分析了不同传感器的影响，发现当在注册和验证时使用不同的传感器时，跨传感器匹配性能会下降。鉴于我们的分析，我们提出了针对这个问题的未来研究方向。
