README.md

metadata

title: Digit Recognition API
emoji: 🔢
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: mit

🔢 Digit Recognition API

A machine learning model that recognizes handwritten digits (0-9) with high accuracy.

🚀 Features

• Real-time prediction of handwritten digits
• REST API for integration with external applications
• Web interface for testing and demonstration
• High accuracy trained model

📡 API Usage

Endpoint

POST https://huggingface.co/proxy/your-username-digit-recognition.hf.space/api/predict

Request Format

Send a POST request with an image file:

import requests

# Upload image file
files = {'data': open('digit_image.png', 'rb')}
response = requests.post(
    "https://huggingface.co/proxy/your-username-digit-recognition.hf.space/api/predict",
    files=files
)

result = response.json()
print(f"Predicted digit: {result['digit']}")
print(f"Confidence: {result['confidence']:.2%}")

Response Format

{
  "digit": "7",
  "confidence": 0.95,
  "status": "success"
}

🔧 Local Development

1. Install dependencies:

pip install -r requirements.txt

2. Run the app:

python app.py

3. Open http://localhost:7860

📋 Model Requirements

• Input: RGB images resized to 64x64 pixels
• Output: Digit classification (0-9)
• Format: Pickled scikit-learn compatible model

🤝 Usage in Applications

Perfect for:

• Educational tools
• Document digitization
• Form processing
• Mobile applications
• Web services

📞 Support

For issues or questions, please open an issue in this space.