应用于物联网设备快速准确的虹膜分割方法

Fast and accurate iris segmentation on IoT devices

随着物联网设备用户数量的增长,物联网设备的安全性已成为人们关注的热点。在多种生物特征认证方法中,虹膜识别由于其具有高安全性而被视为极具前景的认证方法。然而虹膜识别没有成为基于生物特征认证方法的首选,这主要的原因是虹膜识别对于环境因素的严重依赖,环境噪声将导致分割的虹膜区域不准确,无法保证虹膜识别系统的稳定性。为了使虹膜分割能够应用于非理想的虹膜图像中,促进虹膜识别认证在物联网设备上的部署,提出了一种基于深度学习的快速准确的虹膜分割方法。研究在公共的虹膜数据集上进行了实验,实验的结果证明了本文的方法针对非理想虹膜图像进行分割时的有效性,并且提高了虹膜识别系统在物联网设备上的可用性。

With the growth of IoT devices,the security of IoT devices has become a hot spot of concern.In a variety of biometric authentication methods,iris recognition is considered a promising authentication method due to its high security.However,iris recognition has not become the preferred bio-metric authentication method.The main challenge is the severe dependence of iris recognition on environmental factors,which can produce inaccurate segmentation of the iris region,and cause the instability of iris recognition.To enable iris segmentation to be applied to non-ideal iris images,and facilitate deployment of iris recognition authentication on IoT devices,the paper proposes a fast and accurate iris segmentation method based on deep learning.The paper performs experiments on public iris datasets,the results demonstrate the effectiveness of proposed segmentation method for nonideal iris images,and the proposed method improves the usability of iris recognition on IoT devices.