Accurate vessel segmentation using maximum entropy incorporating line detection and phase-preserving denoising
详细信息 查看全文
- 作者：Dinesh Pandey ; dinesh.pandey@live.vu.edu.au ; Xiaoxia Yin ; Hua Wang ; Yanchun Zhang
- 关键词：Line detection ; Phase-preserving denoising ; Morphological operation ; Maximum entropy ; Retinal image segmentation
- 刊名：Computer Vision and Image Understanding
- 出版年：2017
- 出版时间：February 2017
- 年：2017
- 卷：155
- 期：Complete
- 页码：162-172
- 全文大小：2631 K
- 卷排序：155
文摘
An automatic, accurate and computationally efficient framework for retinal blood vessel segmentation is proposed. A preprocessing step that includes background estimation and subtraction to eliminate non-uniform illumination and noise is developed. Local phase preserving denoising works efficiently for thin vessel extraction. Treating thin and thick vessels separately allows accurate segmentation of retinal vessels.