https://github.com/joemathew2004/digit_recognition-cnn
A Streamlit web application that recognizes handwritten digits (0-9) using a Convolutional Neural Network trained on the MNIST dataset. Draw digits on an interactive canvas and get real-time predictions with confidence scores.
https://github.com/joemathew2004/digit_recognition-cnn
cnn-model digit-recognition mnist-dataset neural-network python streamlit tensorflow
Last synced: about 1 month ago
JSON representation
A Streamlit web application that recognizes handwritten digits (0-9) using a Convolutional Neural Network trained on the MNIST dataset. Draw digits on an interactive canvas and get real-time predictions with confidence scores.
- Host: GitHub
- URL: https://github.com/joemathew2004/digit_recognition-cnn
- Owner: joemathew2004
- Created: 2025-06-19T08:45:53.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-19T09:06:49.000Z (about 1 year ago)
- Last Synced: 2025-06-19T09:43:26.649Z (about 1 year ago)
- Topics: cnn-model, digit-recognition, mnist-dataset, neural-network, python, streamlit, tensorflow
- Language: Python
- Homepage:
- Size: 0 Bytes
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Digit Recognition using CNN
A Streamlit web app for handwritten digit recognition using a CNN model trained on MNIST dataset.
## Features
- Interactive drawing canvas
- Real-time digit prediction
- Confidence score display
## Installation
1. Clone the repository
2. Install dependencies:
```bash
pip install -r requirements.txt
```
## Usage
Run the app:
```bash
streamlit run app.py
```
Draw a digit (0-9) in the canvas and click "Predict" to see the result.
## Files
- `app.py` - Main Streamlit application
- `mnist_cnn_model.keras` - Trained CNN model
- `requirements.txt` - Python dependencies