计算机应用 ›› 2019, Vol. 39 ›› Issue (9): 2575-2579.DOI: 10.11772/j.issn.1001-9081.2019030511

• 人工智能 • 上一篇    下一篇

基于眼底图像层次特征的分类方法

余林芳, 邓伏虎, 秦少威, 秦志光   

  1. 电子科技大学 信息与软件工程学院, 成都 610054
  • 收稿日期:2019-03-27 修回日期:2019-05-11 发布日期:2019-05-16 出版日期:2019-09-10
  • 通讯作者: 邓伏虎
  • 作者简介:余林芳(1992-),女,四川达州人,博士研究生,主要研究方向:大数据处理、医学图像处理、数据挖掘;邓伏虎(1984-),男,四川遂宁人,讲师,博士,主要研究方向:信息安全、大数据、网络资源管理;秦少威(1997-),男,河南郑州人,主要研究方向:机器学习、大数据分析;秦志光(1956-),男,四川隆昌人,教授,博士,CCF会员,主要研究方向:医学图像处理、计算机网络、信息安全、密码学、信息管理、智能交通、电子商务、分发和中间件。
  • 基金资助:

    国家自然科学基金面上项目(61672135);四川省科技支撑计划项目(2018GZ0236,2017FZ0004)。

Classification Method Based on Hierarchical Features of Fundus Images

YU Linfang, DENG Fuhu, QIN Shaowei, QIN Zhiguang   

  1. College of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu Sichuan 610054, China
  • Received:2019-03-27 Revised:2019-05-11 Online:2019-05-16 Published:2019-09-10
  • Supported by:

    This work is partially supported by the National Natural Science Foundation of China (61672135), the Sichuan Science and Technology Support Plan Program (2018GZ0236, 2017FZ0004).

摘要:

针对眼底图像中视网膜血管结构的划分问题,提出一种自适应的广度优先搜索算法。首先,基于视网膜血管的结构提出层次特征的概念并进行特征提取;然后,对分割的视网膜血管进行分析及处理,提取得到多个无向图子图;最后,使用自适应的广度优先搜索算法对每个子图中的层次特征进行分类。视网膜血管结构的划分问题被转化为层次特征的分类问题,通过对视网膜血管中的层次特征进行分类,包含这些层次特征的视网膜血管段的层次结构就可以被确定,从而实现视网膜血管结构的划分。该算法运用于公开的眼底图像数据库时具有良好的性能。

关键词: 眼底图像, 层次特征, 结构划分, 血管分支, 分类算法

Abstract:

To solve the problem of retinal vascular structure division in fundus images, an adaptive breadth-first search algorithm was proposed. Firstly, based on the structure of retinal vessels, the concept of hierarchical features was proposed and feature extraction was carried out. Then, the segmented retinal vessels were analyzed and processed, and several undirected subgraphs were extracted. Finally, the adaptive breadth-first search algorithm was used to classify the hierarchical features in each subgraph. The division of retinal vascular structure was transformed into the classification of hierarchical features. By classifying the hierarchical features of retinal vessels, the hierarchical structures of retinal vascular segments containing these hierarchical features were able to be determined, thus realizing the division of retinal vascular structures. The algorithm has excellent performance when applied to public fundus image databases.

Key words: fundus image, hierarchical feature, structure division, bifurcation, classification algorithm

中图分类号: