---
title: OCR Demo
emoji: 👀
colorFrom: green
colorTo: purple
sdk: gradio
sdk_version: 4.43.0
app_file: app.py
pinned: false
license: apache-2.0
---

Check out the configuration reference at https://huggingface.co./docs/hub/spaces-config-reference

# OCR Web Application

This project is an Optical Character Recognition (OCR) application built using PaddleOCR and Gradio. It detects both handwritten and printed text from images, identifies specific 'field', 'value' pairs from documents, and provides two downloadable JSON files.

## Features
- Detects and labels text in images.
- Outputs bounding boxes around detected text.
- Generates two JSON files: one with all detected text and bounding boxes, and another with identified 'field', 'value' pairs.

## Installation
You can run this project on Hugging Face Spaces. No local installation is required.

## Usage
1. Upload an image containing text.
2. The application will return an image with bounding boxes and labels.
3. Download the results as JSON files.

## License
MIT License