My master thesis on Traffic Sign Recognition Using Computer Vision

Udacity Self Driving Car Nanodegree - Traffic Sign Classification

This project uses Convolutional Neural Networks (CNN) to recognize traffic signs from images. The model is trained on the German Traffic Sign Recognition Benchmark (GTSRB) dataset and is capable of classifying traffic signs in real-time from live video feeds.

Uses the Resnet-34 Model to Classify Traffic Signs

This Python-based project features an intuitive graphical user interface (GUI) facilitating image uploads for the identification of essential road signs prevalent on streets, including 20kmph, 30kmph, 50kmph, stop, and right turn signs.

Python Projects Complete code with instructions

This project is a multi-class, single-image classification to recognize traffic signs images using Convolutional Neural Networks (CNN).

Traffic Sign Recognition Project for my Internship on Prime Layer

My experiments on machine learning models (YOLOv5, CNN) on identifying traffic signs and traffic lights.

Yolo11 trained on Polish traffic signs (Warsaw and vicinity)

Projects Implemented for the Udacity Self Driving Car Engineer Nanodegree Program

visit the live site hosted on Heroku.com

Verkehrszeichenerkennung mit CNN (GTSRB-Datensatz)

This project implements a neural network using TensorFlow to classify images of traffic signs from the German Traffic Sign Recognition Benchmark (GTSRB) dataset. The model accurately identifies different types of traffic signs, such as stop signs, speed limit signs, and yield signs, among others.

A deep learning project implementing a Convolutional Neural Network (CNN) in TensorFlow to classify German traffic signs. Features parallel image processing, custom model architecture, and 95%+ accuracy on the GTSRB dataset. Built as part of Harvard's CS50 AI course.

It's a simple python script to predict the traffic signs

Convolutional Neural Network using Jupyter Notebooks

Traffic sign detection and recognition using YOLO 93.2% Accuracy