Retinal blood vessel extraction employing effective image features and combination of supervised and unsupervised machine learning methods
作者：
Highlights：
• A combination of supervised and unsupervised machine learning methods is used for extracting the retinal blood vessels.
• The goal of the combined approach is to deal with the problem of intra-class high variance of image features.
• A set of effective features having a significant influence on the accuracy of the vessel extraction is utilized.
• The proposed method is evaluated on three publicly available databases DRIVE, STARE and CHASE_DB1.
• The obtained results demonstrate the better performance of the proposed method compared to the existing methods.
摘要
•A combination of supervised and unsupervised machine learning methods is used for extracting the retinal blood vessels.•The goal of the combined approach is to deal with the problem of intra-class high variance of image features.•A set of effective features having a significant influence on the accuracy of the vessel extraction is utilized.•The proposed method is evaluated on three publicly available databases DRIVE, STARE and CHASE_DB1.•The obtained results demonstrate the better performance of the proposed method compared to the existing methods.
论文关键词：Retina,Blood vessel,Image processing,Vessel extraction,Classification,Clustering
论文评审过程：Received 22 July 2018, Revised 8 December 2018, Accepted 1 March 2019, Available online 2 March 2019, Version of Record 8 March 2019.
论文官网地址：https://doi.org/10.1016/j.artmed.2019.03.001
