Real Time Traffic Sign Recognition

Project Domain: Computer Vision

This repository contains the dataset, code, and web application for real-time traffic sign recognition using convolutional neural networks (CNN) and OpenCV.

Overview

This project focuses on recognizing traffic signs in real-time using images from the German Traffic Sign Recognition Benchmark (GTSRB). The goal is to develop a robust CNN model for accurate traffic sign classification and integrate it into a web application using Flask.

Dataset: The dataset used in this project is the German Traffic Sign Recognition Benchmark (GTSRB). URL: https://benchmark.ini.rub.de/

Technologies Used

• Keras: For building and training the convolutional neural network
• OpenCV (cv2): For image processing and real-time video capture
• Flask: For web application integration
• HTML and CSS: For web pages creation and styling

Repository Structure

• labels.csv: Includes all class labels.
• templates/: Contains HTML files for the web application.
• static/: Contains CSS files for styling the web application.
• app.py: Flask script for web application integration.
• traffic_sign_recognition.py: Script for training the CNN model and recognizing traffic signs.
• my_model.h5: Trained model.
• README.md: This file.

Web Application Snapshots