undouble’s documentation!

|Python |Python Version Sphinx documentation Stars lines of code Downloads per month Downloads in total License Github Forks Open Issues Project Status Medium Blog Colab example repo-size donate


The aim of the `undouble` library is to detect (near-)identical images across an entire system or directory. It works using a multi-step process of pre-processing the images (grayscaling, normalizing, and scaling), computing the image hash, and the grouping of images based on threshold value.

    1. Detects images with a identical image-hash in a specified folder or your entire system.

    1. The threshold can be used to detect near-identical images, such as photo-bursts.

    1. Plots to examine the groupings.

    1. Functionality to systematically undouble.


Your ❤️ is important to keep maintaining this package. You can support in various ways, have a look at the sponser page. Report bugs, issues and feature extensions at github page.

pip install undouble


Input/ Output

Indices and tables