Lire

An Open Source Java Content Based Image Retrieval Library

The LIRE (Lucene Image REtrieval) library provides a simple way to retrieve images and photos based on their color and texture characteristics. LIRE creates a Lucene index of image features for content based image retrieval (CBIR). Three of the available image features are taken from the MPEG-7 Standard: ScalableColor, ColorLayout and EdgeHistogram a fourth one, the Auto Color Correlogram has been implemented based on recent research results. Furthermore simple methods for searching the index and result browsing are provided by LIRE. The LIRE library and the LIRE Demo application as well as all the source are available under the Gnu GPL license.

The LIRE library is part of the Caliph & Emir project and aims to provide the CBIR features of Caliph & Emir to other Java projects in an easy and light weight way.

Please drop me a line if you use LIRE in your project. I would appreciate feedback very much and I will link reference projects. Email: email address (spam protected)

Downloads

Demos

Documentation

Lire Demo

Included with the release the LIRE Demo found its way into the LIRE package. It provides a simple GUI interface for

  • Indexing photos
  • Searching photos
  • Browsing the created index
  • Creating mosaic images based on indexed images (thanks to Lukas Esterle & Manuel Warum for contributed the mosaic-ing code.)

The mosaic creation is described in detail in this post. You can also find a flash based demo of the mosaic creation abilities of Lire.
Visit sourceforge.net to download LireDemo. Note that Java 1.6 is needed for using LIRE Demo.Installation instructions:Lire Demo Screenshot 01

  • Download LIRE Demo from sf.net: download
  • Unzip (or untar) the downloaded files.
  • Ensure that you haveJava 1.6 installed.
  • Start the demo with “java -jar LireDemo.jar” (or with a double click if you are using Windows)

Online Demo

A friend of mine - Roman Kern - put up his all fresh and newly created personal information portal CorvusAlbus featuring Web 2.0 client side data encryption, photo and text blogs, excessive use of style sheets and javascript and … Tada: Similarity search for images. He included LIRE to allow users to search for similar photos.

corvusalbus02.pngWhen you browse through the photos you will find a small find similar link on the upper right corner of the browser window. Using this link you will get all images visually similar to the current one (like shown in the screenshot). One more hint for visiting CorvusAlbus: Don’t go there with MS Internet Explorer, it won’t help you much! Only Firefox, Opera and Konqueror are supported.

© 2004-2007 by Mathias Lux
>> Contents of this page are licensed under the CreativeCommons Attribution 2.5 license <<