getsanjeev / retinal-exudates-detection

exudates detection using hybrid approach (Image Morphology & Machine Learning)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Exudates Segmentation in Fundus Images

In this project, we apply Image morphology & Clustering to get candidates for exudates pixels. Finally a SVM classifier is applied to get segmentation results.

Getting Started

These instructions will get you a copy of the project up and running on your local machine for you to test the algorithms on your own fundus images. The DIARETDB1 database has been used for demonstration here for which we are grateful.

Bloodvessel Segmentation

Check a subsection at BLOOD VESSEL SEGMENTATION


Prerequisites

The following must be installed and configured:

Sample Output

For some image in DIARETDB1:

Following resultant images are produced while segmentation process (different candidates for single profile of fundus):

Final segmentation output :

For any query Feel free to contact :

About

exudates detection using hybrid approach (Image Morphology & Machine Learning)

License:Other


Languages

Language:Python 100.0%