Imagededup: Find duplicate images in Python

Understand the project

Practical overview

Use it when a Python workflow needs to identify repeated or visually similar images in a directory and provide results for review or evaluation.

Python developers building image-processing or computer-vision workflows.
Teams reviewing repeated or near-duplicate product images and other collection assets.

Before you choose

The repository is public and the package is distributed under the Apache 2.0 license. The README documents PyPI and source installation.

Choose among four hashing methods and CNN-based detection according to the image-matching task.
CNN methods support prepackaged models or a custom model.
The evaluation framework requires a ground-truth mapping to assess deduplication effectiveness.
The README cautions that benchmark conclusions are valid only through v0.2.2 because later releases changed the methods.
The documented quick start generates encodings from a directory and returns a duplicate mapping; it does not describe automatic file deletion.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Generate perceptual-hash encodings for an image directory, identify duplicates and plot matches for a selected file.

Install the package with the command below, or clone the repository and install it with the command below.
Documented command
```
pip install imagededup
```
Documented command
```
pip install .
```
Import PHash from imagededup.methods and create a hasher.
Call encode_images with the image directory, then pass the resulting encoding map to find_duplicates.
Use plot_duplicates with the directory, duplicate map and a filename to plot matches for that file.

A duplicate mapping for the directory and a plot of matches associated with the selected image.

This recipe uses PHash; the README also offers other hash methods and CNN-based approaches.
The guide describes finding and plotting matches, not deleting or otherwise changing image files.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 15 October 2026
Original website title: idealo/imagededup · Official homepage title · retained in its source language