东北大学学报(自然科学版) ›› 2022, Vol. 43 ›› Issue (4): 496-501.DOI: 10.12068/j.issn.1005-3026.2022.04.006

• 信息与控制 • 上一篇    下一篇

基于YOLOV3改进的虹膜定位算法

于哲舟1,3, 刘岩2,3, 刘元宁1,3   

  1. (1. 吉林大学 计算机科学与技术学院, 吉林 长春130012; 2. 吉林大学 软件学院, 吉林 长春130012; 3. 吉林大学 符号计算与知识工程教育部重点实验室, 吉林 长春130012)
  • 修回日期:2021-06-10 接受日期:2021-06-10 发布日期:2022-05-18
  • 通讯作者: 于哲舟
  • 作者简介:于哲舟(1961-),男,吉林长春人,吉林大学教授,博士生导师; 刘元宁(1962-),男,吉林长春人,吉林大学教授,博士生导师.
  • 基金资助:
    国家重点研发计划项目(国科发资【2020】151号); 吉林省产业创新专项资金资助项目(2019C053-2).

Improved Iris Locating Algorithm Based on YOLOV3

YU Zhe-zhou1,3, LIU Yan2,3, LIU Yuan-ning1,3   

  1. 1. College of Computer Science and Technology, Jilin University, Changchun 130012, China; 2. College of Software, Jilin University, Changchun 130012, China; 3. Key Laboratory of Symbolic Computing and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China.
  • Revised:2021-06-10 Accepted:2021-06-10 Published:2022-05-18
  • Contact: LIU Yuan-ning
  • About author:-
  • Supported by:
    -

摘要: 针对传统虹膜定位算法定位不准确的问题,利用改进的YOLOV3虹膜定位模型对虹膜定位的准确率加以提高,使其更好应用于生产实践.使用Densenet-121模型作为特征提取模块,并在此基础上通过复制骨干网络得到辅助网络的方式使其更有利于检测小目标,用Non-local注意力机制增强图片获取特征语义信息.采用基于DarkNet-53的YOLOV3模型、Daugman模型及Wilde模型进行对比实验.实验结果表明:本文的实验模型在虹膜定位中的准确率高达97.1%,与其他虹膜定位模型相比具有明显优势.

关键词: YOLOV3;虹膜定位;特征提取;目标检测;注意力机制

Abstract: Aiming at the problem of inaccurate locating of traditional iris locating algorithms, an improved YOLOV3 iris locating model is proposed to improve the accuracy of iris locating and make it better applied to production practice. Using the Densenet-121 model as the feature extraction module, and on the basis of it, the auxiliary network is obtained by copying the backbone network to make it more conducive to the detection of small targets, and the non-local attention mechanism is used to enhance the semantic information of the features obtained by the image. The YOLOV3 model, Daugman model and Wilde model based on DarkNet-53 are used for comparative experiments. The experimental results show that the accuracy of the experimental model in this paper is as high as 97.1% in iris locating, which has obvious advantages compared with other iris locating models.

Key words: YOLOV3; iris registration; feature extraction; object detection; attention mechanism

中图分类号: