Find and delete duplicate images inside a directory.

Running

> python main.py -d 'sample_images/'
[DUPLICATE FOUND] sample_images/road.jpg sample_images/road_duplicate.jpg
[DELETED] sample_images/road_duplicate.jpg

> python main.py -h
usage: main.py [-h] [-d] [-s] [--min_matches MIN_MATCHES]
               [--features_distance FEATURES_DISTANCE]
               directory

positional arguments:
  directory             directory with the images

optional arguments:
  -h, --help            show this help message and exit
  -d, --delete          delete the duplicate images found with smaller res
  -s, --silent          quiet execution without logging
  --min_matches MIN_MATCHES
                        minimum number of matching features to accept the
                        images as being similar
  --features_distance FEATURES_DISTANCE
                        [0,1] - higher number results in more matching
                        features but with less accuracy

Similar / Duplicate Images

Different Images

Requirements

Before running this project you need to install its requirements.

> pip install -r requirements.txt

Built With

• Python - Programming language
• OpenCV - Computer vision library

License

This project is licensed under the MIT License - see the LICENSE.md file for details.

References

• D. G. Lowe, "Distinctive image features from scale-invariant keypoints", International Journal of Computer Vision, 60, 2 (2004), pp. 91-110. [PDF]
• M. Muja and D. G. Lowe, "Scalable Nearest Neighbor Algorithms for High Dimensional Data", IEEE Transactions on Pattern Analysis and Machine Intelligence 36, 11 (2014), pp. 2227-2240. [PDF]