Skin Disease Detection

Project Title

Skin Disease Detection

Project Area of Specialization Artificial IntelligenceProject Summary

Our project is about skin disease detection, in which we have worked on 4 major diseases happening in Pakistan

 Which are 'Acne and Rosacea Photos',

 'Eczema Photos',

 'Nail Fungus and other Nail Disease',

 'Warts Molluscum and other Viral Infections’.

We have trained our model using Convolutional neural network which is a class in deep learning , most commonly applied to analyze visual image.

After model training we have built an API through which we will integrate our model to website.

At final user will upload an image on website and it will detect these among these 4 and gave it name.

Project Objectives

?The objective of this project is to identify skin disease based on the input skin images texture analysis based on thresholding and neural network to detect and diagnose skin disease.

?We have worked on 4 main diseases which mostly happen in Pakistan.

1.Acne and Rosacea

2.Eczema

3.Nail Fungus and other Nail Disease

4.Warts Molluscum and other Viral Infections

This Project will predict among these 4 diseases.

Project Implementation Method

Defining all working in FYP-1:

1. Flow Diagram of Project.
2. Data collection.
3. Data cleaning and preprocessing.
4. Model Training.
5. Testing Validation and training accuracy.
6. As accuracy was low, trained model once again with more dataset and increased number of epochs for better training.
7. Model trained with good accuracy.
8. API made for model to be integrated with some Website.
9. API working perfect with good results.

FYP -2 Remaining things described below:

• Some more testing of model for better accuracy.
• Website to be build.
• Integration of model and website.
• Host website on server.
• Put model on cloud or docker image.

Benefits of the Project

The proposed system is able to detect the skin disease with promising results combining computer vision and machine learning techniques.

It can be used to help people from all over the world and can be used in

doing some productive work.

The tools used are free to use and are available for the user, hence, the

system can be deployed free of cost.

The application developed is light-weight and can be used in

machines with low system specifications.

 It has also a simple user interface for the convenience of the

user.

The image processing and machine learning algorithms were successfully implemented.

Technical Details of Final Deliverable

We have worked on these application:

•Jupyter Notebook for model training.

•API Work on Pycharm IDE.

•Postman for testing backend.

Languages:

•Python 3.9

Final Deliverable of the Project Software SystemCore Industry HealthOther IndustriesCore Technology OthersOther TechnologiesSustainable Development Goals Good Health and Well-Being for PeopleRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	0
NONE	Miscellaneous	0	0	0