Human Recognition based on Remote Video Capture of Eye Movements and Blinking

随着先进技术越来越多地融入我们的日常生活，为了提高安全性和隐私性并减少规避风险，对可靠的生物特征认证和身份识别系统的需求比以往任何时候都更加明显。尽管精度很高，但目前的生物识别技术依赖于特定的物理特征，如指纹、面部和虹膜特征，很容易受到欺骗和伪造。因此，我们确实需要开发更可靠的生物识别解决方案，用于人类识别，能够在不需要特定动作（例如将手指放在扫描仪上或查看虹膜相机）的情况下持续识别/认证人们。在这个项目中，我们提出了一个基于眼部运动和眨眼的远程视频捕捉的人类识别的可行性研究。提出的基于眼动追踪数据的解决方案提供了一个更灵活的设计，眼球运动和眨眼模式被从更远的距离拍摄的视频记录下来，这是非侵入性的，更容易分析，更难以欺骗。此外，它还提供了一个额外的优势，即提取用于生物识别的相同特征可用于确定疲劳或其他生理状况或行为变化。

With increasing integration of advanced technologies into our daily life, the need of reliable biometricauthentication and identification systems is more pronounced than ever before in order to improve security andprivacy and to reduce the risk of circumvention. Despite high accuracy, current biometric technologies relyingon particular physical features such as fingerprints, face and iris characteristics are vulnerable to spoofing andforgery. Therefore, there is a real need for development of more reliable biometric solutions for humanrecognition that are able to continuously identify/authenticate people without requiring specific actions fromthem (e.g. placing fingers on an scanner or looking into an iris camera). In this project, we propose a feasibilitystudy on human recognition based on remote video capture of eye movements and blinking. The proposedsolution based on eye tracking data offers a more flexible design, where eye movement and blinking patternsare captured on video recordings taken from greater distance which is non-intrusive, simpler to analyze andmore difficult to spoof. Furthermore, it offers an added advantage where the same features extracted forbiometric recognition can be used for determining fatigue or other physiological conditions or behavioralchanges.