https://github.com/tushar-shinde31/blood_group_detection_using_fingerprint-flask-

A Flask-based ML application that predicts blood groups using fingerprint images. It integrates a TensorFlow (Keras) model with 89% accuracy, featuring user authentication, database management with Flask SQLAlchemy & SQLite, and a frontend built using flask. 🚀
https://github.com/tushar-shinde31/blood_group_detection_using_fingerprint-flask-

css deep-learning flask flask-application html javascript kaggl machine-learning neural-networks svm svm-model third-year-project vgg16

Last synced: 3 months ago
JSON representation

A Flask-based ML application that predicts blood groups using fingerprint images. It integrates a TensorFlow (Keras) model with 89% accuracy, featuring user authentication, database management with Flask SQLAlchemy & SQLite, and a frontend built using flask. 🚀

• Host: GitHub
• URL: https://github.com/tushar-shinde31/blood_group_detection_using_fingerprint-flask-
• Owner: Tushar-Shinde31
• Created: 2024-12-25T16:34:13.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2025-04-28T16:44:09.000Z (5 months ago)
• Last Synced: 2025-04-28T17:46:25.574Z (5 months ago)
• Topics: css, deep-learning, flask, flask-application, html, javascript, kaggl, machine-learning, neural-networks, svm, svm-model, third-year-project, vgg16
• Language: HTML
• Homepage:
• Size: 6.6 MB
• Stars: 7
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 🩸 Blood Group Prediction Using Fingerprint

## 📌 Project Overview

This project introduces a **non-invasive** approach to blood group prediction using **fingerprint image processing** and **machine learning**. By leveraging **Convolutional Neural Networks (CNNs)**, it classifies fingerprint patterns into **eight common blood groups** (A+, A-, B+, B-, AB+, AB-, O+, O-), offering a **quick** and **accessible** alternative to traditional methods.

![home](https://github.com/user-attachments/assets/8479c8a4-98ef-4b6c-aac7-247df2eb3cd2)

## 🎥 Demo Video

[Watch the demo on YouTube](https://youtu.be/BCwa5xclfk0?si=_o926diqvEMfQuql)

---

## 🎯 Objectives

✅ **Rapid Blood Group Identification** – Provides a fast and accurate alternative to traditional methods.

✅ **Accessibility in Remote Areas** – Enables blood group prediction without lab facilities or skilled personnel.

✅ **Integration with Portable Devices** – Supports point-of-care diagnostics in clinics and mobile units.

✅ **Safety and Scalability** – Reduces contamination risks and ensures adaptability across healthcare settings.

✅ **Biometric and Medical Synergy** – Combines biometrics and machine learning for improved diagnostics.

---

## 🛠️ Tech Stack

### 🌐 Frontend:

- HTML

- CSS

- JavaScript

### 🔥 Backend:

- Flask

- SQLAlchemy

- SQLite

### 📊 Machine Learning (Model Development):

- TensorFlow / Keras

- Google Colab

---

## 📈 Model Performance

| 🧠 Model                             | 🎯 Testing Accuracy | 📊 Validation Accuracy |

|--------------------------------------|---------------------|------------------------|

| **VGG16**                            | ✅ 88.72%           | ✅ 89.50%              |

| **AlexNet**                          | 🔴 12.47%           | 🔴 12.49%              |

| **ResNet50**                         | 🟡 61.19%           | 🟡 62.70%              |

| **Hybrid Model (EfficientNetB0 + SVM)** | 🔵 22.29%           | 🔵 22.81%              |

---

## 📚 Dataset

[📂 Fingerprint Dataset](https://www.kaggle.com/datasets/rajumavinmar/finger-print-based-blood-group-dataset)

### 📊 Dataset Overview:

![dataset](https://github.com/user-attachments/assets/ccc93bf9-f1b4-490f-9767-aeca4800e98a)

---

## 📸 Screenshots

### 🔐 Authentication Page

![auth2](https://github.com/user-attachments/assets/1eadbb89-7a9c-4b98-b3e9-f2e4f05d4707)

![auth1](https://github.com/user-attachments/assets/1ee2b462-2684-4479-9db3-769f3920e2c0)

### 🔍 Prediction Result Page

![prediction](https://github.com/user-attachments/assets/4076fbbe-de88-46a6-b4fc-209da889158c)

### 📤 Upload Fingerprint

![upload](https://github.com/user-attachments/assets/3ba4768c-b462-46ab-aaf9-680808f344ec)

---

## 🚀 Future Improvements

- 📊 **Expand the dataset** for better generalization.

- 🧪 **Experiment with advanced models** to improve accuracy.

- 🌐 **Deploy the model** in a live environment for real-world use.

---

## 📞 Contact

### 👤 **Tushar Shinde**

📧 [tusharshinde2250@gmail.com](mailto:tusharshinde2250@gmail.com)  

🔗 [LinkedIn](https://www.linkedin.com/in/tushar-shinde-262335257/)

### 👤 **Anjali Maske**

📧 [aamaske50@gmail.com](mailto:aamaske50@gmail.com)  

🔗 [LinkedIn](https://www.linkedin.com/in/anjali-maske/)

---

⭐️ **Feel free to contribute and star the repository if you find it helpful!**