LIRE: Lucene Image Retrieval

LIRE is a Java library that provides a simple way to retrieve images and photos based on color and texture characteristics. LIRE creates a Lucene index of image features for content based image retrieval (CBIR) using local and global state-of-the-art methods. Easy to use methods for searching the index and result browsing are provided. Best of all: it's all open source.

LIRE is successfully used at the WIPO, a United Nations Agency, to search in millions of trademark images and the Danish National Police to find similar scenes and to detect near duplicates. LIRE also works well with the Apache Solr search server.

Features Overview

LIRE works on platforms supporting Java 8 and has been tested on Windows and Linux. Test it on a million images with the web demo.
Responsive Layout

Open Source

LIRE comes without secrets. All the state of the art algorithms are available in source.

Retina Graphics

State of the Art

Well known and well performing local and global features are integrated.

Powerful Performance

Powerful Performance

Using approximate search LIRE scales well to millions of images.

Responsive Layout

Endless Possibilities

Take control over every step in the process, tinker with extraction, indexing and search.

Retina Graphics

Solr Plugin

There is a plugin for the popular Apache Solr search server and a docker image.

Powerful Performance

Research Driven

Fresh & new algorithms from the visual information retrieval community.

LIRE is Open Source Software

No need to pay a high price when it comes for free. No need to look for proprietary solutions, when source code is available.

GNU GPL License

LIRE is published under the viral OSS Licene, the GNU Public License. Therefore, it will stay free.

Hosted on Github

LIRE source is hosted and managed on Github. Check out revisions, submit patches and more.

Open Communication

Anything you need to know? Ask on the LIRE mailing list. We are happy to help you!

Lots of examples

Developers will find everything to start with at the developers' docs. Even sample applications for common tasks are available.

It even has a book

Visual Information Retrieval using Java and LIRE (English Edition), written by Mathias Lux and Oge Marques is available on Amazon

De-Facto Reference Software

For many of the global descriptors LIRE is the de-facto reference implementation, also in research.

Consulting Services for LIRE

Content based image retrieval & visual information retrieval experts at your service for affordable rates.

Are you stuck with using LIRE?

  • Tailored Sample Code
  • Source Code Reviews
  • Performance Tests & Profiling
  • Custom Features & Metrics
  • Evaluations based on your Data
  • Consultation on Feature Selection
Interested?

Testimonials

LIRE is actively used in research and industry.
  • Michael Riegler

    I used LIRE in several projects. And I am really impressed. It is very flexible, provides powerful tools and at the same time it is easy to use.

    Michael Riegler SIMULA Research, Norway
  • Gerald Friedland

    LIRE was a huge help for our research in multimedia by allowing us to quickly extract visual features for our baseline processing pipeline.

    Gerald Friedland Director, Audio and Multimedia, ICSI
  • Damian Borth

    We used Lire for the extraction of visual features for the YFCC100m dataset. It is a great tool providing a broad set of different image descriptors, all wrapped in a robust and efficient library.

    Damian Borth Head of Multimedia Analysis and Data Mining, DFKI
  • Customer Testimonials

    LIRE is a fantastic product. We are using LIRE in production and are now able to index and retrieve our multimedia in much more sophisticated ways. Combining LIRE with Hadoop/SOLR means that we can scale the solution. What a joy.

    Marc Bailerey Software Developer, Danish National Police, NC3