Skip to content

MreenalRanjan23/Blood_Group_Detection_Using_Fingerprint

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Blood-Group-Detection-Using-Fingerprint

A deep learning project that uses a Convolutional Neural Network (CNN) to predict a person’s blood group from fingerprint images. Built with PyTorch and Flask, this web app allows users to upload fingerprint images and get instant blood group predictions.

Features

  • Uses CNN to analyze fingerprint images.
  • Supports 8 blood group classes.
  • Includes training, validation, and testing pipeline.
  • Web interface for uploading fingerprint images and getting predictions.
  • Confusion matrix and performance metrics visualization.

Dataset

The dataset used for training was obtained from Kaggle: 🔗Fingerprint-Based Blood Group Dataset: https://www.kaggle.com/datasets/rajumavinmar/finger-print-based-blood-group-dataset Please download it separately and place it in the appropriate folder before training.

How to Run the Project

Model Training

To train the model run: python Scripts/train_model.py Ensure the dataset is placed correctly before training.

🔐 Authentication

Simple login and registration system using SQLAlchemy and PostgreSQL. Update the SQLALCHEMY_DATABASE_URI in app/init.py with your own credentials.

📄 License

This project is licensed under the MIT License. See the LICENSE file for more details.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors