Traffic Signs CNN

TRAFFIC SIGN CLASSIFICATION

With the major advancements in self driving cars and smart cars has given way to a new classification problem for identifying traffic signs. The self-driving cars require the ability to know the current speed limit, stop signs, etc. Also, some car manufacturers can use a classification system to identify the traffic sign and notify the driver. Convolutional neural networks or ConvNets are a great way to classify images and thus can be used to classify traffic signs (3).
Explore the docs »

· Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Description
4. Contributing
5. License
6. Contact

About The Project

Built With

• Powerpoint
• Word
• jupyter notebook

Getting Started

To get a local copy up and running follow these simple steps.

Prerequisites

• Microsoft Office Suite
• PDF Reader

Installation

1. Clone the repo

   git clone https://github.com/AMeyer89/TrafficSigns.git
   

Description

This project demonstrates how to use a convolutional neural network to classify traffic signs. Cars have come a long way and require traffic sign detection. Convolutional neural networks or ConnvNets are a great way to classify images and thus can be used to classify traffic signs. The data used was preprocessed German traffic signs that were saved into the nine pickle files (6). The dataset has 43 types of signs, classes. Training subset contains 86989 images, validation subset contains 4410 images and testing subset contains 12630 images. The model was validated using accuracy. The results showed that the model performed well with a testing accuracy of more than 77%. All models used the same parameters, but different filter dimensions of 3 X 3, 5 X 5, 9 X 9, and 13 X 13. The classification accuracy equal to 89.6%, 82.9%, 80.1% and 77.8 %

Contributing

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

License

Distributed under the MIT License. See LICENSE for more information.

Contact

April Meyer - swim53185@gmail.com

Project Link: https://github.com/AMeyer89/TrafficSigns