https://github.com/alinababer/finger-print-generation-and-discrimination-by-dcgan

This project focuses on the generation and authentication of fingerprints using Adaptive Deep Convolution Generative Adversarial Networks (ADCGAN).
https://github.com/alinababer/finger-print-generation-and-discrimination-by-dcgan

dcgan deep-learning gan generative-adversarial-network generative-ai opencv python

Last synced: about 2 months ago
JSON representation

This project focuses on the generation and authentication of fingerprints using Adaptive Deep Convolution Generative Adversarial Networks (ADCGAN).

• Host: GitHub
• URL: https://github.com/alinababer/finger-print-generation-and-discrimination-by-dcgan
• Owner: AlinaBaber
• Created: 2022-12-27T07:49:24.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-10-27T11:05:00.000Z (3 months ago)
• Last Synced: 2024-10-27T12:49:04.381Z (3 months ago)
• Topics: dcgan, deep-learning, gan, generative-adversarial-network, generative-ai, opencv, python
• Language: Jupyter Notebook
• Homepage:
• Size: 1.33 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Fingerprint Generation and Authentication using ADCGAN

This project leverages **Adaptive Deep Convolutional Generative Adversarial Networks (ADCGAN)** for generating and authenticating fingerprint images, crucial for applications like mobile security, biometrics, and airport systems.

## Overview

Fingerprints are unique and widely used for secure authentication. This project employs deep learning with ADCGAN to generate realistic fingerprints and authenticate them with a high degree of accuracy, achieving **92% authentication accuracy**.

## Key Features

- **Fingerprint Synthesis**: Generates realistic fingerprints using ADCGAN.

- **Fingerprint Authentication**: Authenticates fingerprints generated with ADCGAN.

- **High Accuracy**: 92% accuracy on the Socofing fingerprint dataset.

- **Application Areas**: Useful for secure access in mobile, biometric systems, and more.

## Getting Started

### Prerequisites

- Python 3.x

- Required Libraries: `tensorflow`, `keras`, `torch`, `opencv-python`, `numpy`, `matplotlib`

### Installation

1. Clone the repository:

   ```bash

   git clone https://github.com/username/Fingerprint-Generation-Authentication-ADCGAN.git

## Results

Accuracy: The ADCGAN model achieved 92% accuracy on the test set.

Generated Samples: Sample generated fingerprints can be found in the results/ directory.

## Demostration

https://github.com/user-attachments/assets/e451fdbf-c9a8-4cb6-9c4c-008a70c55179

## Applications

This project has potential applications in:

Mobile Security: Fingerprint-based access control

Biometric Systems: Secure identity verification

Airport & Public Safety: Reliable biometric identification systems

## Reference

For more details, refer to my full paper: [Fingerprint Generation and Authentication using ADCGAN](https://ieeexplore.ieee.org/document/10178664)

Additionally, you can find more information here: [Semantic Scholar](https://www.semanticscholar.org/paper/Fingerprint-generation-and-authentication-though-Mustafa-Zehra/a810bb649e887f80476d4deecae786049616da19)