Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
CBIR with LIReMathias LuxKlagenfurt UniversityAustria            This work is licensed under the Creative Commons Attribut...
Lucene Image Retrieval• Open source• Java• Based on Lucene  – text retrieval engine
History• Caliph & Emir  – first release in July 2004  – developed since ~ midth of 2003• Lire as spin-off product  – first...
Image Retrieval Features• Color Histograms• MPEG-7 features    – scalable color, color layout and edge histogram• Tamura f...
Indexing and Search• Fast linear search• BoVW search based on Lucene• Parallel k-means & visual word indexing  for BoVW• F...
Lire: Some Examples• Utilize Lucene  – put an index into RAM  – distribute indexes over the network• Rapid prototyping  – ...
Where has LIRe been used?• ImageCLEF  – different groups  – mentioned on the website• TRECVid  – 2010 ranked 3rd in known ...
Future Directions …• Unified way to change & test metrics• Easier benchmarking• Further support and maintenance
Thanks …• Want to download & try LIRe:• http://www.semanticmetadata.net
Upcoming SlideShare
Loading in …5
×

Content based image retrieval with LIRe

5,041 views

Published on

Published in: Technology

Content based image retrieval with LIRe

  1. 1. CBIR with LIReMathias LuxKlagenfurt UniversityAustria This work is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0
  2. 2. Lucene Image Retrieval• Open source• Java• Based on Lucene – text retrieval engine
  3. 3. History• Caliph & Emir – first release in July 2004 – developed since ~ midth of 2003• Lire as spin-off product – first release in 2006 – first use case was „barrique“ – Just MPEG-7 Barrique is a project of Roman Kern: http://sourceforge.net/projects/barrique/
  4. 4. Image Retrieval Features• Color Histograms• MPEG-7 features – scalable color, color layout and edge histogram• Tamura features – coarseness, contrast and directionality• Joint histograms CEDD, FCTH and JCD• Auto color correlation• JPEG coefficients histogram• Local features – SIFT , SURF, MSER• ... and more to come
  5. 5. Indexing and Search• Fast linear search• BoVW search based on Lucene• Parallel k-means & visual word indexing for BoVW• Fastmap for spatial indexing• Metric spaces approach for fast search in global features
  6. 6. Lire: Some Examples• Utilize Lucene – put an index into RAM – distribute indexes over the network• Rapid prototyping – Basic auto-tagging < 100 loc• Test different features & approaches – eg. mediamid & CEDD
  7. 7. Where has LIRe been used?• ImageCLEF – different groups – mentioned on the website• TRECVid – 2010 ranked 3rd in known item search• Medical domain – image retrieval & video summarization• Apparel search applications
  8. 8. Future Directions …• Unified way to change & test metrics• Easier benchmarking• Further support and maintenance
  9. 9. Thanks …• Want to download & try LIRe:• http://www.semanticmetadata.net

×