Handwritten-Digit-Recognition-with-Deep-Learning-on-MNIST-Dataset

Developed a deep learning model to accurately classify handwritten digits from the MNIST dataset.

Overview

This project involves the implementation of a deep learning model using Convolutional Neural Networks (CNN) to recognize and classify handwritten digits from the famous MNIST dataset. The MNIST dataset is a large database of handwritten digits that is commonly used for training various image processing systems. The model was trained to achieve high accuracy in classifying digits from 0 to 9.

Project Structure

• Data Preprocessing: Data normalization and reshaping for better performance.
• Training: Model trained using the Adam optimizer with categorical cross-entropy loss.
• Evaluation: The model was evaluated on the test set with high accuracy.

Key Features

• High Accuracy
• Real-Time Prediction

Dataset

The MNIST dataset, which includes 60,000 training images and 10,000 testing images, was used for training and evaluating the model. Each image is a 28x28 grayscale image representing a digit from 0 to 9.

Requirements

• Python 3.x
• TensorFlow
• Keras
• NumPy
• Matplotlib

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License