---
title: "Zeronine Handwriting Wizard"
url: "https://ridwaanhall.com/projects/zeronine-handwriting-wizard"
markdown: "https://ridwaanhall.com/projects/zeronine-handwriting-wizard.md"
summary: "A CNN-based web app that recognises handwritten Arabic and English digits and characters."
---

# Zeronine Handwriting Wizard

> A CNN-based web app that recognises handwritten Arabic and English digits and characters.

- Category: Machine Learning
- Status: Maintenance Support
- Started: August 14, 2024
- Built with: CNN, Python, Django, TensorFlow, Keras, NumPy, Jupyter Notebook, Vercel
- Source: https://github.com/ridwaanhall/zeronine

## About

### The problem

Handwriting recognition demos usually cover English digits only, while many people in Indonesia write in both Arabic and Latin scripts.

### The approach

I built Zeronine end to end: collecting data, training convolutional neural networks with TensorFlow and Keras, and deploying a Django web app for live recognition.

- Recognition of Arabic and English digits and characters.
- CNN models trained for high classification accuracy.
- A complete path from data collection to a deployed website.

### The result

Zeronine shows the full machine learning lifecycle in one project, from raw data to a usable bilingual recognition tool.

## Features

- **Bilingual Recognition**: Recognises Arabic and English digits and characters.
- **CNN Models**: Convolutional neural networks for accurate classification.
- **End-to-End**: Covers data collection, training and deployment.

## Tags

Django, Handwritten Digit Recognition, Model, Zeronine

## Elsewhere

- This page for people: https://ridwaanhall.com/projects/zeronine-handwriting-wizard
- Index of every page as Markdown: [llms.txt](https://ridwaanhall.com/llms.txt)
