https://github.com/ProvenanceLabs/image-match

🎇 Quickly search over billions of images
https://github.com/ProvenanceLabs/image-match

image-analysis image-signatures python search

Last synced: about 19 hours ago
JSON representation

🎇 Quickly search over billions of images

• Host: GitHub
• URL: https://github.com/ProvenanceLabs/image-match
• Owner: rhsimplex
• Created: 2016-03-08T18:16:45.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2022-12-06T11:29:04.000Z (almost 2 years ago)
• Last Synced: 2024-05-23T04:39:53.855Z (4 months ago)
• Topics: image-analysis, image-signatures, python, search
• Language: Python
• Homepage:
• Size: 1.5 MB
• Stars: 2,919
• Watchers: 101
• Forks: 406
• Open Issues: 64
• Metadata Files:
  • Readme: README.md
  • License: LICENSES.md

Awesome Lists containing this project

README

        
# NOTE: this repository is no longer maintained; PRs and issues will probably be ignored. If you are interested in taking over development/maintainership of image-match, please contact me at the email address in my public profile. Thank you!

[![PyPI](https://img.shields.io/pypi/status/image-match.svg?maxAge=2592000)](https://pypi.python.org/pypi/image-match)

[![PyPI](https://img.shields.io/pypi/v/image-match.svg)](https://pypi.python.org/pypi/image-match)

[![Documentation Status](https://readthedocs.org/projects/image-match/badge/?version=latest)](https://image-match.readthedocs.org/en/latest/)

[![codecov](https://codecov.io/gh/edjolabs/image-match/branch/master/graph/badge.svg)](https://codecov.io/gh/edjolabs/image-match)

![image-match](https://cloud.githubusercontent.com/assets/6517700/17741093/41040a64-649b-11e6-8499-48b78ddca56b.png)

image-match is a simple (now Python 3!) package for finding approximate image matches from a

corpus.  It is similar, for instance, to [pHash](http://www.phash.org/), but

includes a database backend that easily scales to billions of images and

supports sustained high rates of image insertion: up to 10,000 images/s on our

cluster!

**PLEASE NOTE:** This algorithm is intended to find nearly duplicate images -- think copyright

violation detection.  It is **NOT** intended to find images that are conceptually similar.

For more explanation, see [this issue](https://github.com/edjo-labs/image-match/issues/62) or

[this video](https://www.youtube.com/watch?v=DfWLBzArzKE).

Based on the paper [_An image signature for any kind of image_, Wong et

al](http://www.cs.cmu.edu/~hcwong/Pdfs/icip02.ps).  There is an existing

[reference implementation](https://www.pureftpd.org/project/libpuzzle) which

may be more suited to your needs.

The folks over at [Pavlov](https://usepavlov.com/) have released an excellent

[containerized version of image-match](https://github.com/pavlovml/match) for

easy scaling and deployment.

## Quick start

### [Install and setup image-match](http://image-match.readthedocs.io/en/latest/start.html)

Once you're up and running, read these two (short) sections of the documentation to get a feel

for what image-match is capable of:

### [Image signatures](http://image-match.readthedocs.io/en/latest/signatures.html)

### [Storing and searching images](http://image-match.readthedocs.io/en/latest/searches.html)