Praveenterax/Traffic-sign-Detection-Recognition-Matlab-RandomForest

Detect traffic sign and recognize them using Image Processing algorithms and Machine Learning(Random Forest)

Traffic Sign Detection and Recognition using Random Forest Classifier

Detect and recognize traffic signs using image processing algorithms and machine learning(Random Forest algorithm) --- Accuracy 94%
Explore the docs »

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
3. Usage
4. Contact

About The Project

Detect and recognize traffic signs using Image Processing algorithms and Machine Learning(Random Forest) with an accuracy of 94%.

Datasets used:

• GTSDB
• GTSRB

Due to time constraint and computational limitations, the dataset has been intentionally reduced to 16000 files. To use entire dataset, try adding more masks!

(back to top)

Built With

• MATLAB
• Image Processing
• Machine Learning

(back to top)

Getting Started

This entire project can be fragmented in to two parts:

• Detection
• Recognition

Prerequisites

Things required to make the project a success:

• Knowledge of Image Processing
• Getting around Matlab
• Machine Learning
• Never give up attitude!

Usage

After Image detection has been done!

• Open Hog Feature Extraction file and make the required changes upon your requirement and run it.
• HOG Features will be saved to avoid extraction for every execution.
• Open Training and Model Accuracy file to train the model with extracted features.

  Change the number of decision trees for your desired accuracy! Also check the ROC-AUC and Precision-Recall curves.

• The model will be saved locally.

  Saving time varies from computer to computer

• Move all masks to the current directory so that, Main Funtion file will be in the same level as masks.
• Run the Main Funtion file and you are good to go!!....

(back to top)

Contributing

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

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!

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

(back to top)

Contact

Your Name - Praveenterax - praveendunga789@gmail.com

Project Link: https://github.com/Praveenterax/Traffic-sign-Detection-Recognition-Matlab-RandomForest

(back to top)