MNIST Numerical Handwriting OCR using TensorFlow Keras

Created By Charunthon Limseelo, advised by Arnon Monkong from SPECTRE Thailand

This repository contains a Python implementation of a handwritten digit recognition system using the MNIST dataset and TensorFlow's Keras API. The MNIST dataset is a widely used dataset in the field of machine learning and computer vision, consisting of 28x28 pixel grayscale images of handwritten digits (0 to 9). The goal of this project is to build a deep learning model that can accurately recognize and classify these handwritten digits.

Features

• Data Preprocessing: The MNIST dataset is preprocessed to prepare it for training. This includes normalization and reshaping of the input data.
• Neural Network Architecture: The repository implements a convolutional neural network (CNN) using TensorFlow's Keras API. CNNs are well-suited for image recognition tasks and have been proven effective on the MNIST dataset.
• Training and Evaluation: The model is trained on the training data and evaluated on the test data to measure its accuracy and performance.
• Prediction: The trained model can be used to predict the digits in new handwritten images.

Prerequisites

Before you begin, ensure you have met the following requirements:

• Python 3.9 or later
• TensorFlow
• Keras
• Matplotlib (for visualizing the data and training progress)

Getting Started

1. Clone the repository:

   git clone https://github.com/chrnthnkmutt/MNIST_Tensorflow_ipynb.git

2. Change your directory to the project folder:

   cd MNIST_Tensorflow_ipynb

After that, you just play along the instructions that I described within Jupyter Notebook files.

Usage

The files those I included in the repositiory are quite different throught the difficulty of different learners who starts or try to be expert to learn on Machine Learning and Artificial Intelligence. So that, I decided to create on both version, the easier and full-version one.

Contributing

Contributions are welcome! If you find any bugs or have enhancements to propose, please submit an issue or create a pull request explaining the issue or feature.

License

This project is licensed under the MIT License

Happy coding!