CallMeDaniel's picture
Update README.md
4310789 verified

A newer version of the Gradio SDK is available: 5.7.1

Upgrade
metadata
title: Form Understanding Project - Certificate of Diagnosis
emoji: πŸ“
colorFrom: pink
colorTo: green
sdk: gradio
sdk_version: 4.11.0
app_file: app.py
pinned: true

Form Understanding Project - Certificate of Diagnosis πŸ‘€

Welcome to the Form Understanding Project focused on Certificates of Diagnosis! This project leverages advanced OCR technology and deep learning to enhance the extraction and processing of information from medical certificates of diagnosis. Our aim is to streamline the handling of these documents, making it easier and more efficient for healthcare providers and insurance companies.

Project Vision

This endeavor stands as a testament to the power of integrating OCR (Optical Character Recognition) and key information extraction (KIE) into an end-to-end system designed to redefine the approach to document analysis, specifically targeting medical certificates.

Features

  • Accurate Text Detection and Recognition: Utilizing cutting-edge OCR models to detect and recognize text in certificates of diagnosis with high accuracy.
  • Multilingual Support: Capable of handling documents in multiple languages, making it versatile for diverse medical environments.
  • Template Adaptation: Incorporates common Taiwanese medical document templates for better recognition and processing.
  • Integration with Insurance Systems: Designed to work seamlessly with insurance claim processing systems, particularly optimized for FUBON LIFE INSURANCE CO., LTD.

Technology Stack

  • Scene Text Detection: Employing advanced techniques for detecting text in various scenes to accurately identify text regions in medical documents.
  • Scene Text Recognition: Leveraging state-of-the-art models for recognizing text within the detected regions, ensuring high accuracy in text extraction.
  • PaddleOCR: Powered by PaddlePaddle from Baidu, ensuring robust and efficient OCR capabilities.

Join us in revolutionizing the way certificates of diagnosis are processed and managed. Your contributions and feedback are welcome!

Contact

For any inquiries or contributions, please reach out to Daniel Du.