This app finds duplicate to near duplicate images by generating a hash value for each image stored with a specialized data structure called VP-Tree which makes searching an image on a dataset of 100Ks almost instantanious
3rd update:
- Added a log of actions tab
- Better support for drag n drop
- Fixed various crashes and better error handling
- Upgraded the quality of code
2nd update:
- Replaced OpenCV with Pillow
- Various Small Fixes to prevent crashing
- Added Progress bar
- Added Splash Logo (with more UI Plans on future updates) Thanks to Creative Force
1st update:
- Deprecated .ui & success.wav file
- Added "always on top" on settings
- Decreased possible crashes on drag n drop
Online examples of this are Google images & TinEye which return near duplicate results from images they indexed across the web
On the left you can see the given image (for the example it's slightly different from the original) and on the right the result
- You can also drag n drop an image from browser! (Firefox / Chrome tested)
- Python 3.7+ (haven't tested with older versions)
required versions of the Python 3 modules can be found on the requirements.txt
Pyqt6 is used but works with PyQt5 too if you update the app.py file modules import
pip install -r /path/to/requirements.txt
pip3 install -r /path/to/requirements.txt
run app.py to start
settings.ini will be created on the directory
Hashing Pickle & VPTree pickle files will be created on the first index
Special Thanks to Adrian Rosebrock for his tutorials that made this possible
Detailed Guide how everything works and step by step make your own