Traffic Sign Classification with Convolutional Neural Network (CNN)
This project implements a Convolutional Neural Network (CNN) using the Keras library to classify traffic sign images. The dataset used for training the model contains 43 different classes of traffic signs. The trained model is then integrated into a simple graphical user interface (GUI) using Tkinter, allowing users to upload an image and get real-time predictions of the corresponding traffic sign.
-
CNN Architecture: The model architecture includes convolutional layers, max-pooling layers, dropout layers, and dense layers to effectively learn and classify traffic sign patterns.
-
Data Preprocessing: Images are loaded, resized, and converted to NumPy arrays for training. One-hot encoding is applied to the labels.
-
Training and Evaluation: The model is trained on a training dataset, and the training history is visualized using Matplotlib. The model's performance is evaluated on a test dataset using accuracy metrics.
-
GUI for Classification: The Tkinter-based GUI allows users to upload an image, and the trained model classifies the traffic sign in real-time.
- Clone Repository:
git clone https://github.com/your-username/traffic-sign-classification.git cd traffic-sign-classification