Research Article
Self-organizing Map for Blood Vessel Segmentation of Fundus Images
2 downloads
@INPROCEEDINGS{10.1007/978-3-030-66785-6_14, author={Jingdan Zhang and Le Wang and Yingjie Cui and Lili Guo and Wuhan Jiang}, title={Self-organizing Map for Blood Vessel Segmentation of Fundus Images}, proceedings={Machine Learning and Intelligent Communications. 5th International Conference, MLICOM 2020, Shenzhen, China, September 26-27, 2020, Proceedings}, proceedings_a={MLICOM}, year={2021}, month={1}, keywords={Wavelet transform Fundus images Self-organizing map}, doi={10.1007/978-3-030-66785-6_14} }- Jingdan Zhang
Le Wang
Yingjie Cui
Lili Guo
Wuhan Jiang
Year: 2021
Self-organizing Map for Blood Vessel Segmentation of Fundus Images
MLICOM
Springer
DOI: 10.1007/978-3-030-66785-6_14
Abstract
Blood vessel segmentation is a topic of high interest in fundus image analysis. This paper presents a clustering method to segment the blood vessels automatically from the fundus images. Our proposed method integrates with the wavelet transform, the morphological transformation and self-organizing map (SOM). Firstly, we extract a multi-dimensional feature vector of every pixel in the fundus image by wavelet transform and morphological operation. Then, the SOM network is integrated with K-mean method to cluster pixels. Finally, we validate the accuracy of our proposed method on DRIVE database, and compare our proposed method with other methods.
Copyright © 2020–2025 ICST
