SemanticMetadata.net » Lire

LIRe presentation and poster at ACM MM 2011

Mathias Lux — Tue, 29 Nov 2011 22:18:02 +0000

Just finished my presentation at ACM MM’s open source competition in 2011. Many interested researchers and developers came by to discuss ideas and developments. I’m looking forward to turning many of those idea into code

For those of you interested in the poster I uploaded it here.

I also uploaded the presentation to slideshare.

Searching with Lire in big datasets

Mathias Lux — Thu, 27 Oct 2011 09:17:34 +0000

Having received several complaints about the slowness of Lire when searching in 100k+ documents I took my time to write a small how to to explain approaches for search in big (relatively) data sets.

Lire has the ability to create indexes with lots of different features (descriptors, like RGB color histograms or CEDD). While this opens the opportunity to flexibility at search time as we can select the feature at the time we create a query, the index tends to get bigger and bigger and searcher take longer and longer.

With a data set of 121,379 images the index created with the features selected for default in Lire Demo has a size of 14,3 GB on the disk. In contrast to that an index just storing the CEDD feature along with the image identifier has a size of 29 MB.

Due to the size of the index also linear search tends to get slower. While for the index stripped down to the CEDD feature and the identifier searching takes (on a AMD Quad-Core computer with 4GB RAM and Java 1.7) roughly 0.33 seconds, searching the big index takes 7 minutes and 3 seconds.

So if you want to index and search big data sets (> 100.000 images for instance) I recommend to

select which features you need,
create the index with a minimum set of features, and
eventually split the index per feature and select the index on the fly instead of the feature
also you can load the index into RAM

For more on loading the index to RAM and the option to use local features read on in the developer wiki.

Lire publication in the top 10 downloads of ACM SIGMM

Mathias Lux — Mon, 24 Oct 2011 12:42:48 +0000

As to be found in this month’s SIGMM record, which is the electronic SIGMM newsletter, a publication about Lire is in the top 10 downloads of the ACM special interest group on multimedia for September 2011.

I co-authored the paper with Savvas Chatzichristofis:

Mathias Lux, Savvas A. Chatzichristofis. Lire: lucene image retrieval: an extensible java CBIR library. In ACM Multimedia 2008

It’s also the paper I recommend to include in references if Lire is used within a scientific publication, so my thanks also go to the authors citing and therefore pointing to our work!

Lire and Lire Demo v 0.9 released

Mathias Lux — Thu, 20 Oct 2011 11:37:23 +0000

I just released Lire and Lire Demo in version 0.9 on sourceforge.net. Basically it’s the alpha version with additional speed and stability enhancements for bag of visual words (BoVW) indexing. While this has already been possible in earlier versions I re-furbished vocabulary creation (k-means clustering) and indexing to support up to 4 CPU cores. I also integrated a function to add documents to BoVW indexes incrementally. So a list of major changes since Lire 0.8 includes

Major speed-up due to change and re-write of indexing strategies for local features
Auto color correlation and color histogram features improved
Re-ranking filter based on global features and LSA
Parallel bag of visual words indexing and search supporting SURF and SIFT including incremental index updates (see also in the wiki)
Added functionality to Lire Demo including support for new Lire features and a new result list view

Download and try:

Source and binaries (or as tar.bz2)
Lire Demo

Lire Demo 0.9 alpha 2 just released

Mathias Lux — Fri, 05 Aug 2011 10:41:46 +0000

Finally I found some time to go through Lire and fix several of the — for me — most annoying bugs. While this is still work in progress I have a preview with the demo uploaded to sf.net. New features are:

Auto Color Correlogram and Color Histogram features improved
Re-ranking based on different features supported
Enhanced results view
Much faster indexing (parallel, use -server switch for your JVM)
Much faster search (re-write of the searhc code in Lire)
New developer menu for faster switching of search features
Re-ranking of results based on latent semantic analysis

You can find the updated Lire Demo along with a windows launcher here, Mac and Linux users please run it using “java -jar … ” or double click (if your windows manager supports actions like that

Download Liredemo v0.9 alpha 2

The source is — of course — GPL and available in the SVN.

My Talk at BarCamp / CreateCamp Klagenfurt

Mathias Lux — Mon, 07 Feb 2011 17:00:40 +0000

On Saturday I gave a talk on LIRe & the art of content based image retrieval at the 5th BarCamp in Klagenfurt. Although few people followed my talk we had lively and interesting discussion, especially on the application in the site politinserate.at. If you are interested, find the slides on SlideShare (in german, sorry folks).

Visual Attention in Lire

Mathias Lux — Mon, 22 Mar 2010 16:44:19 +0000

While doing my preparations for my multimedia information systems lecture I finally came around to implement the visual attention model of Stentiford myself. I just check in the sources (SVN). The algorithm gives actually really nice results compared to its actual simplicity (implementationwise). You can see an example in the following figure. On the left hand side there is the original image and on the right hand side a visualization of the attention map. The light areas (especially the white ones) are deemed centers of attention. Sky and sand are so to say just random noise (there is a lot of “random” in this approach).

Links

F. W. M. Stentiford, “An estimator for visual attention through competitive novelty with application to image compression,” Proc. Picture Coding Symposium, pp 101-104, Seoul, 24-27 April, 2001.

Search through a million images in less than a second

Mathias Lux — Sat, 20 Mar 2010 09:00:02 +0000

We reached a milestone here! Sebastian Kielmann reported that he used LIRe to index a million images. While that’s actually no problem he further managed to search through the images in < 1 second! Whoot!

Sebastian used the metric index, which implements the ideas of Giuseppe Amato. The approach is easy, but works out really fine. Currently CEDD is the standard descriptor, but others are integrated easily. However, using the metric index is not trivial and requires some knowledge on the process. Also the results are approximate and might differ from the results obtained by linear search.

Links

LIRe development mailing list

Mathias Lux — Fri, 19 Mar 2010 15:17:56 +0000

Few weeks ago I was asked if there is a mailing list dedicated to LIRe and development of applications with LIRe. That was reason enough for moe to create one. The mailing list is available at Google Groups and it’s called lire-dev. Please feel free to subscribe and ask (and of course answer and discuss) any questions regarding LIRe.

Links

LIRe Dev Google Group

Lire 0.8 released

Mathias Lux — Thu, 11 Mar 2010 15:15:33 +0000

I just released LIRe v0.8. LIRe – Lucene Image Retrieval – is a Java library for easy content based image retrieval. Based on Lucene it doesn’t need a database and works reliable and rather fast. Major change in this version is the support of Lucene 3.0.1, which has a changed API and better performance on some OS. A critical bug was fixed in the Tamura feature implementation. It now definitely performs better Hidden in the depths of the code there is an implementation of the approximate fast indexing approach of G. Amato. It copes with the problem of linear search and provides a method for fast approximate retrieval for huge repositories (millions?). Unfortunately I haven’t tested with millions, just with tens thousands, which proves that it works, but it doesn’t show how fast.

Links

Download Lire & Lire Demo