https://github.com/jonnoftw/pdf_img_diff

Compare images between assignments
https://github.com/jonnoftw/pdf_img_diff

opencv pdf plagiarism-detection python

Last synced: 21 days ago
JSON representation

Compare images between assignments

• Host: GitHub
• URL: https://github.com/jonnoftw/pdf_img_diff
• Owner: JonnoFTW
• Created: 2018-12-05T03:49:16.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2018-12-06T03:44:01.000Z (almost 6 years ago)
• Last Synced: 2024-10-14T03:01:18.442Z (about 1 month ago)
• Topics: opencv, pdf, plagiarism-detection, python
• Language: Python
• Size: 1.01 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# PDF Image Diff

A simple tool that checks a folder of PDF files to see if there are similar or matching images occuring between documents.

### Installation

```bash

pip install git+https://github.com/JonnoFTW/pdf_img_diff.git

```

### Usage

```

pdf-img-diff /path/to/folder/ -v 

```

Will output a report saying which files have matching images between them.

If you want you can also specify a method

## Methods

Currently these methods are supported:

* SSIM: Structural similarity index. This is the default and my recommendation

* [KAZE](https://www.doc.ic.ac.uk/~ajd/Publications/alcantarilla_etal_eccv2012.pdf)  

* Histogram comparison: doesn't work very well

## Future work

Look into comparisons of feature points using:

* ORB

* SIFT

* SURF

* BRIEF

This might be useful https://www.researchgate.net/publication/323561586_A_comparative_analysis_of_SIFT_SURF_KAZE_AKAZE_ORB_and_BRISK