Segmentation and Classification of Diabetic Retinopathy

Get Dataset By Clicking:

https://drive.google.com/file/d/19U-hV_g3OwIVSNb72HeIJl6gWt1vj39T/view?usp=sharing

GOAL

• Image sampling using k-mean clustering
• Image segmentation
• Image classification using ML, ANN, and CNN models

Requirements:

To run the code, you will need the following libraries:

• Numpy
• OpenCV
• Tensorflow
• Sklearn
• opencv
• matplolib

Running the Code:

The code can be run using a Jupyter Notebook file. Follow the steps below to get started:

1. Install Jupyter Notebook on your computer if you don't already have it installed
2. Clone or download the project repository
3. Open the Jupyter Notebook file in the repository
4. Run the cells in the notebook to execute the code

Image Sampling:

The first step in the project is to sample the images using k-mean clustering. This step involves grouping similar images together and using them for analysis.

Image Segmentation:

The second step is to perform image segmentation, which involves dividing the image into multiple segments or regions of interest. This step helps to identify the areas of the eye that are affected by diabetic retinopathy.

Image Classification:

The final step involves using machine learning algorithms such as ANN, CNN, or other ML models to classify the images based on the presence or absence of diabetic retinopathy.

Conclusion:

This project demonstrates a simple approach to detect diabetic retinopathy in eye images using machine learning techniques. Further improvements can be made by using more advanced models and techniques to improve the accuracy of the results.