https://github.com/horizon-blue/scanner

Scans documents using your camera :)
https://github.com/horizon-blue/scanner

Last synced: about 2 months ago
JSON representation

Scans documents using your camera :)

• Host: GitHub
• URL: https://github.com/horizon-blue/scanner
• Owner: horizon-blue
• License: gpl-3.0
• Created: 2017-12-04T03:13:20.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2017-12-13T19:30:04.000Z (over 7 years ago)
• Last Synced: 2025-04-02T02:48:59.399Z (2 months ago)
• Language: Python
• Homepage: https://xiaoyan5.web.illinois.edu/cs445/project/
• Size: 49.7 MB
• Stars: 11
• Watchers: 4
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Scanner

Scans documents using your camera :)

## Installation

```sh

# install python modules

pip3 install -r requirements.txt

# install tesseract (OCR dependency)

# Example: MacOS

# See https://github.com/tesseract-ocr/tesseract for more details

brew install tesseract --with-all-languages

```

## Run the Scanner

```sh

python3 main.py 

```

The output will be stored in `./result/` directory

## Demo

Input Image:

![input](./example/input.jpg)

Boundary Recognition:

![contour](./example/contour.jpg)

Transform using homography:

![transofrm](./example/transofrm.jpg)

Recognize text location:

![text location](./example/overlay.jpg)

Remove text from background:

![background](./example/inpaint.jpg)

Translate and transform the translated text using reverse homography:

![translated](./example/font.jpg)

Merge the text back to the background

![final](./example/final.jpg)