This project implements a deep neural network (DNN) model for traffic sign recognition using the German Traffic Sign Recognition Benchmark (GTSRB) dataset. The goal is to accurately classify traffic sign images into their respective categories.
- Python 3.x
- TensorFlow 2.x
- NumPy
- Pandas
- Matplotlib
- OpenCV (cv2)
- PIL (Python Imaging Library)
- scikit-learn
The GTSRB dataset is used for training and evaluating the model. It can be downloaded from the following link: GTSRB Dataset.
The dataset contains images of 43 different traffic sign classes, with varying sizes and lighting conditions.
- Clone the repository.
- Install the required dependencies.
- Place the GTSRB dataset in the appropriate folder within the project structure.
- Run the SAR_GTSRB_DNN_ImageClassifiee.py script to train and evaluate the DNN model.
The trained DNN model achieves an accuracy of XX% on the test dataset. This indicates its effectiveness in recognizing and classifying traffic sign images.
This project is licensed under the MIT License.
Feel free to use, modify, and distribute this code for your own purposes.
GTSRB Dataset: https://benchmark.ini.rub.de/gtsrb_dataset.html