Welcome to Img3Sum’s documentation!

Img3Sum is an Open-source project that supports translating, summarizing and converting images to text.

Introduction

The purpose of this tool is to organize text images into three lines for those who are not fluent with English and who don’t want to read the entire English document

Features

1. Optical character recognition of an image file with English text

2. Summarize extracted English text to 3 sentences

3. Translate summarized English text to Korean

4. (planned) check for grammatical errors in extracted English text

5. (planned) Optical character recognition of an image file with Korean text

Demos

Contents

• Installation
  • Prerequisites
  • External Source
• How to use?
  • Running on Localhost
  • Running each feature with python
  • Hosting with External URL
• Contributing Guidelines
  • How Can I Contribute?
• LICENSE

Release

v 0.0.1

Authors

• Joonwon Jang - Github: Lainshower

• GeonYeong Son - Github : GeonYeongSon

• YiYoung Yoon - Github : y20ng

• JuHeon Oh - Github : OZOOOOOH