https://github.com/magwyz/pastec

Image recognition open source index and search engine
https://github.com/magwyz/pastec

Last synced: 2 months ago
JSON representation

Image recognition open source index and search engine

• Host: GitHub
• URL: https://github.com/magwyz/pastec
• Owner: magwyz
• License: lgpl-3.0
• Created: 2014-08-21T09:43:07.000Z (over 10 years ago)
• Default Branch: dist-ver
• Last Pushed: 2023-01-09T21:33:42.000Z (about 2 years ago)
• Last Synced: 2024-08-04T04:02:43.459Z (6 months ago)
• Language: C++
• Homepage: http://pastec.io
• Size: 195 KB
• Stars: 618
• Watchers: 49
• Forks: 174
• Open Issues: 14
• Metadata Files:
  • Readme: README.md
  • License: COPYING

Awesome Lists containing this project

• starred-awesome - pastec - Image recognition open source index and search engine (C++)

README

        
Pastec

======

Introduction

------------

### Presentation

[Pastec](http://www.pastec.io) is an open source index and search engine for image recognition based on [OpenCV](http://www.opencv.org/). It can recognize flat objects such as covers, packaged goods or artworks. It has, however, not been designed to recognize faces, 3D objects, barcodes, or QR codes.

Pastec can be, for example, used to recognize DVD covers in a mobile app or detect near duplicate images in a big database.

Pastec does not store the pixels of the images in its database. It stores a signature of each image thanks to the technique of [visual words](http://en.wikipedia.org/wiki/Visual_Word).

Pastec offers a tiny HTTP API using JSON to add, remove, and search for images in the index.

### Intellectual property

Pastec is developed by [Visualink](http://www.visualink.io) and licenced under the [GNU LGPL v3.0](http://www.gnu.org/licenses/lgpl.html).

It is based on the free packages of [OpenCV](http://www.opencv.org/) that are available for commercial purposes; you should therefore be free to use Pastec without paying for any patent license.

More precisely, Pastec uses the [patent-free ORB descriptor](https://www.willowgarage.com/sites/default/files/orb_final.pdf) and not the well-known SIFT and SURF descriptors that are patented.

Setup

-----

See [here](http://pastec.io/doc#setup).

API

---

See [here](http://pastec.io/doc#api)