This repository contains the implementation of a Contactless Palm Recognition Biometric System. The system utilizes state-of-the-art palm recognition technology to provide secure and convenient biometric authentication. It offers a contactless and user-friendly approach for various applications.
- Project Description
- Features
- Image Processing Techniques
- Preprocessing
- Feature Extraction
- Installation
- Usage
- Technology Stack
The Palm Recognition Biometric System is designed to identify and authenticate individuals based on their unique palmprint patterns. It offers a secure and convenient way to access various services and systems without the need for physical contact.
- Contactless Palmprint Capture: Utilize a camera to capture palmprint images without physical contact.
- Real-time Recognition: Achieve real-time palmprint recognition for seamless and efficient authentication.
- User-Friendly Interface: Provide an intuitive user interface for easy enrollment and authentication.
The Palm Recognition Biometric System leverages advanced image processing techniques to achieve accurate and reliable palmprint recognition. These techniques play a crucial role in extracting relevant features from palmprint images and performing efficient matching.
- Image Resizing: Resize captured palmprint images to a standardized resolution for consistent feature extraction.
- Contrast Enhancement: Apply techniques like Histogram Equalization and Contrast Limited Adaptive Histogram Equalization (CLAHE) to improve image contrast and enhance palmprint details.
- Region of Interest (ROI) Detection: Locate and extract the palm region from the captured image using techniques like Object Detection to find the palm first and crop the palm.
- Clone this repository:
git clone https://github.com/yourusername/palm-recognition.git
- Install the required dependencies:
pip install -r requirements.txt
- Run the application:
python main.py
- Python: Programming language used for development.
- OpenCV: Library for computer vision and image processing.
- Deep Learning: Leveraged for palmprint feature extraction and recognition.
- GUI Library: Pyqt5 to create an interactive user interface.