Handwritten Digit Recognition

Abstract

1. Introduction

The MNIST database (Modified National Institute of Standards and Technology database) of handwritten digits consists of a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger set available from NIST. Additionally, the black and white images from NIST were size-normalized and centered to fit into a 28x28 pixel bounding box and anti-aliased, which introduced grayscale levels.

An implementation of multilayer neural network using keras with an accuracy of 98.314% and using tensorflow with an accuracy over 99%.

A neural network is made up by stacking layers of neurons, and is defined by the weights of connections and biases of neurons. Activations are a result dependent on a certain input.

2. Objective

This project demonstrates Handwritten digit recognition using Deep Learning

This project demonstrates how Jupyter Notebook, Python, Machine Learning can be applied to a real-world AI & Machine Learning problem.

4. Technology Stack

5. System Requirements

General requirements for this technology stack — check the README for exact versions.

• Python 3.8 or later with Jupyter Notebook / JupyterLab (or Google Colab)
• pip for dependencies
• Python 3.8 or later
• pip / virtualenv for dependencies
• VS Code, PyCharm or Jupyter Notebook
• Git (to clone the repository)

6. Installation & Setup

git clone https://github.com/aakashjhawar/handwritten-digit-recognition.git
cd handwritten-digit-recognition

1. You can also run the load_model.py to skip the training of NN. It will load the pre saved model from model.json and model.h5 files.

git clone https://github.com/aakashjhawar/Handwritten-Digit-Recognition.git
cd Handwritten-Digit-Recognition
pip3 install -r requirements.txt
python3 tf_cnn.py

python3 load_model.py <path/to/image_file>

python3 load_model.py assets/images/1a.jpg

Full setup instructions are in the project README.

7. Future Enhancements

Suggested extensions you can add to make this your own project.

• Deploy the model as a web app with Streamlit, Flask or FastAPI
• Compare against an additional model and report the metric difference
• Add explainability (SHAP / Grad-CAM)

8. Viva / Review Questions

Common questions examiners ask for projects in this domain.

1. What dataset does the project use and how was it pre-processed?
2. Which algorithm / model architecture is used and why was it chosen over alternatives?
3. How are training and testing data split, and how is overfitting avoided?
4. Which evaluation metrics (accuracy, precision, recall, F1) are reported and what do they mean here?
5. How would you deploy this model for real users?

9. Source Code & License

This project is developed by aakashjhawar and published on GitHub under the MIT License. Please follow the license terms and credit the original author when you use or modify this code.