Retinal Disease detection

Published on 02 Jul 2021. Written by Palvi Soni

The Eye is the gift of God to us for visualizing the beauty of the world. Eyes need to have cared because it is easily affected by retinal disease. Retinal diseases can impact the vision of the eye to a great extent that can sometimes lead to blindness. Glaucoma is one of the major cause of blindness. It is serious diseases that do not show any symptoms in the early stage.

SLNOTE

Programming environment

MATLAB- MATLAB is used for the implementation of this project. There is a default image processing box in MATLAB that can enhance the working of the system. There are mathematical tools that provide image contrast and image intensity. In nutshell, MATLAB is equipped with various features that support full image processing and image classification techniques.

We deployed MATLAB 2019 a version for this purpose.

Project implementation

In this image processing project firstly collect images from any online source and apply image processing techniques on it to find relevant output.

SLLATEST
1. Retinal Images acquisition

Firstly, collect images from dataset that can be available on different online sources and you can also collect these images manually by visiting some eye care hospitals and add them into your database.

2. Image Enhancement

After adding images into database choose any image of your choice and apply image enhancement techniques on it such as histogram equalization so as to improve contrast in images.

3. ROI Extraction and selection

ROI extraction is a region of interest in which only intended portion is selected and the rest of the portion is discarded. Only on the selected portion, the image processing techniques are applied.

4. Apply Thresholding

After ROI extraction and selection, apply thresholding on it. Thresholding is used to convert grayscale images into binary images.

5. Apply Segmentation technique

On binary image the appropriate segmentation techniques are applied so as to separate portions of the eye which have the disease or which do not have disease.

6. Removal of noise

Again, after application of thresholding, it is the time to remove unwanted noise from the retinal images.

7. Retinal image smoothing

Retinal image smoothing further enhances the images so that disease will be detected with full accuracy and precision.

8. Classification

For classification of retinal images whether the eye is affected by the disease or not we use the classification method for this. Either SVM or we can use Naive Bayes classifier for classifying the disease.

In Naïve Bayes diseases are classified on the basis of probability

9. Detection of disease

After classification the affected area is easily detected.

We can calculate performance parameters after that.

Advantages of this project

It generates an accurate result.
It saves times.
It generates minimum errors.

SLDYK
Kit required to develop Retinal Disease detection:

JAVA

Technologies you will learn by working on Retinal Disease detection:

Retinal Disease detection

Any Questions?

Subscribe for more project ideas