Traffic Sign Recognition

Implementation of a Convolutional Neural Network for classification of traffic signs using Keras.

Usage

Code can be accessed through the provided Jupyter Notebook file.

Dependencies

• Keras
• OpenCV
• Matplotlibb
• Numpy
• Tensorflow
• Pandas
• Seaborn
• imageio

Dataset

• GTSRB dataset is used in this project.
• Download the dataset here and update dataset folder location in the notebook.
• Original dataset source: http://benchmark.ini.rub.de/?section=gtsrb&subsection=dataset
• The dataset consists of 43 different classes of images.

Sample Images from Dataset

CNN Model Details

Following is the summary of the Convolutional Neural Network model used for this problem:

Prediction Results

A random sample from the prediction results of the trained model is below:

Citations

• J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel. The German Traffic Sign Recognition Benchmark: A multi-class classification competition. In Proceedings of the IEEE International Joint Conference on Neural Networks, pages 1453–1460. 2011.

Authors

👤 Asad Bin Khalid

• Github: @asadbinkhalid

👤 Fatima Junaid

• Github: @faatimaajunaid