计算机科学与探索 ›› 2024, Vol. 18 ›› Issue (6): 1421-1437.DOI: 10.3778/j.issn.1673-9418.2312062

• 前沿·综述 • 上一篇    下一篇

基于深度学习的虹膜识别研究综述

江健,张琪,王财勇   

  1. 1. 中国人民公安大学 信息网络安全学院,北京 100038
    2. 北京建筑大学 电气与信息工程学院,北京 100044
  • 出版日期:2024-06-01 发布日期:2024-05-31

Review of Deep Learning Based Iris Recognition

JIANG Jian, ZHANG Qi, WANG Caiyong   

  1. 1. School of Information and Cyber Security, People??s Public Security University of China, Beijing 100038, China
    2. School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China
  • Online:2024-06-01 Published:2024-05-31

摘要: 虹膜识别技术以其卓越的精确性、安全性和稳定性等特点著称。当前的虹膜识别系统在约束用户状态和采集设备的条件下展现出较为稳定的性能,但是无法适应目前复杂多样的开放场景。开放场景中包含大量不确定采集因素,例如采集的虹膜图像容易受到睫毛、头发遮挡和镜面反射等因素的干扰,这些不确定性因素往往会造成图像质量的整体下降,导致虹膜图像分割和特征提取环节性能的显著下降。近年来,深度学习算法已被广泛应用于虹膜识别,旨在提升系统对开放场景的适应性。对深度学习技术在虹膜识别领域的应用现状进行了综述,总结了其在提高开放场景下识别精度的关键作用。首先,介绍了虹膜识别的背景;其次,全面分析了针对虹膜生物识别开发的各类深度学习模型在虹膜分割、特征提取和特征匹配任务中的表现,阐述了它们的优势和局限;然后,系统地总结了常见的虹膜数据集及其特性;最后,指出了虹膜识别任务新挑战以及未来探索的潜在方向。

关键词: 虹膜识别, 生物特征识别, 模式识别, 计算机视觉, 深度学习

Abstract: The highly accurate, secure, and stable biometric technology of iris recognition is well-known. The current iris recognition system shows stable performance under the condition of constraints on user status and acquisition equipment, but it cannot adapt to the current complex and diverse open scenes. Open scenarios contain a large number of uncertain acquisition factors, for example, iris images acquired in open scenarios are easily interfered by factors such as eyelashes, hair blockage, and specular reflection, etc. These uncertainties often lead to an overall decline in image quality, resulting in a significant decline in the performance of iris image segmentation and feature extraction. In recent years, deep learning algorithms have been widely used in iris recognition, aiming to improve the adaptability of the system to open scenarios. The current status of the application of deep learning technology in iris recognition is reviewed, and its key role in improving recognition accuracy in open scenarios is summarized. Firstly, the background of iris recognition is presented. Secondly, the performance of various deep learning models in iris segmentation, iris feature extraction and feature matching tasks is analyzed, and their advantages and limitations are expounded. Then, the common iris datasets and their characteristics are systematically summarized. Lastly, new challenges and potential directions for future exploration of iris recognition are pointed out.

Key words: iris recognition, biometrics, pattern recognition, computer vision, deep learning