Computer based analysis for automated segmentation of blood vessels in retinal images will help eye care specialists screen larger populations for vessel abnormalities. However, automated retinal segmentation is complicated by the fact that the width of retinal vessels can vary from very large to very small, and that the local contrast of vessels is unstable, especially in unhealthy ocular fundus. We propose a novel method that takes these facts into account. Our method includes a multiscale analytical scheme using Gabor filters and scale production, and a threshold probing technique utilizing the features of retinal vessel network. Our method is good for detecting large and small vessels concurrently. It also offers an efficient way to denoise and enhance the responses of line filters, allowing the detection of vessels with low local contrast.
|Number of pages||4|
|Journal||Proceedings - International Conference on Pattern Recognition|
|Publication status||Published - 1 Dec 2006|
|Event||18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong, Hong Kong|
Duration: 20 Aug 2006 → 24 Aug 2006
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition