Scribd
Upload
117 views20 pages

Project

Uploaded by

rishikantorg99
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
117 views20 pages

Project

Uploaded by

rishikantorg99
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 20

Eye Disease

Detection
USING MACHINE
LEARNING
Our Team

Himanshu Prabhakar

Aman Kaim
Saurabh Verma
Anshul Kumar
Agenda
1. Introduction 3. Technologies
involved
5. Conclusion
Problem Terminologies

2. 4.
Final result of this
Objective Methodology/ involved in the project
Approach Project TimeLine
project

Data Collection and All phases of


Preprocessing
Feature Extraction
this project
Model Training
Integration and
Deployment
INTRODUCTION
Problem

According to the National Eye Institute, an estimated 80% of


people with eye disease are unaware of it. This means that a
significant percentage of people who have eye disease do
not know they have it.

Here’s is the reason why?


Eye diseases can be asymptomatic.
Eye diseases can develop slowly over time.
People may not be aware of the importance of eye
exams.
Objective (Solution)

Eye Disease Detection model Eye Test Portal


What does our project do?
This project creates a machine learning system to identify various eye
diseases by analyzing images. Trained on a large dataset of retinal
images, it achieves a promising 85%-90% accuracy in classifying
common conditions like diabetic retinopathy, macular degeneration,
glaucoma, cataracts, and diabetic macular edema.
METHODOLOGY/APPROACH
Data Collection and
Preprocessing

Gather a large dataset of eye images with


corresponding labels indicating the presence or
absence of various eye diseases.
Feature Extraction

Extract relevant features from the


preprocessed images that can effectively
capture the characteristics of different eye
diseases.
Model Training
Select an appropriate machine learning
algorithm for classification
ain the chosen ML model using the
extracted features and their corresponding
disease labels.
Optimize the model's hyperparameters to
maximize its performance.
live
Integration and working
Deployment project
Trained ML model for
eye disease detection
Integrate the trained ML model into a software
application or web service for real-time eye
disease detection.
Develop a user-friendly interface for uploading
eye images and receiving classification results.
User Interface
Back-end (front-end)
TECHNOLOGIES INVOLVED
Technologies involved
in the Project

1. Machine Learning 2. Computer Vision 3. Image Processing


Technologies involved
in the Project

4. Data Preprocessing 5. Algorithm development 6. Software development


Data Handling
PROJECT TIMELINE
PROJECT Phase 4: Back-end User-Interface
development

TIMELINE
Designing the central engine, managing data,
algorithms, and Develop a user friendly interface for
the system
Goal
March 2024
Phase 2: Data collection &
preprocessing
Gather images & data sets from
internet and clean/Enhance them.
Dec 2023
May 2024

phase 5: Integration & testing


Integrating all the component
together and test each of them
working fine.

January 2024
Phase 3: Model Development & validation
Create and train machine
learning model & Evaluate
Nov 2023
model accuracy and reliability
Phase 1: Research & Review
Review relevant research and
collected data
CONCLUSION
CONCLUSION

A machine learning-based system for multiple eye


disease detection was developed and evaluated.

The system achieved an overall accuracy of


85%-90% in detecting common eye diseases.

Machine learning has the potential to revolutionize


eye disease diagnosis and treatment.
Get in Anshul Kumar
Aman Kaim
[email protected]
[email protected]

touch Saurabh Verma


Himanshu Prabhakar
[email protected]
[email protected]

You might also like