- Real-time Traffic Symbol Prediction: Developed an advanced computer vision application leveraging Python, TensorFlow, and OpenCV for real-time traffic symbol recognition.
- LeNet-5 CNN Architecture: Implemented the LeNet-5 Convolutional Neural Network architecture to effectively classify various traffic symbols, resulting in improved prediction accuracy at lower computational cost.
- Image Preprocessing: Skillfully utilized OpenCV for image preprocessing, including resizing, normalization, and augmentation, to enhance the model's generalization capabilities.
Download the dataset from: https://www.kaggle.com/datasets/aritrabose2003/traffic-symbols-dataset
Run the following code in your terminal to install the dependencies:
pip install -r requirements.txt
- Unzip the dataset in the root directory of the project
- Run the following command in your terminal:
python main.py
Run the following command in your terminal:
python test.py