SEO News

All About Content Based Image Retrieval

by , Comments

P.L. has a great summary of a Slashdot post concerning content based image retrieval (CBIR) and research from Penn St. University.

?CBIR? is the handy acronym for Content based image retrieval. Basically, it means instead of entering text to find images, you provide or click on an existing image to find related ones. This ought to be much more intuitive for certain tasks.

A CBIR research project of Penn State University has now been applied to an aviation images database, Slashdot reports. Click on ?Show me photos?, and then click on ?View similar photos? to get an idea of how well this works. This is not necessary related to actual image recognition (analyzing a picture to find out it contains, say, an elephant), but can be implemented using much more brute force pixel-by-pixel image comparison with some added mirror and scaling fuzzyness.

I was hoping to share another CBIR demo caled Image-Seek from LTU Technologies. It allowed you to search and find similar photos from a collection of Corbis images. However, according to the LTU site it's "temporarily unavailable." Oh well, you can still read about it.

Nevertheless, LTU Technolgies (the company was recently acquired) web site offers lots of interesting reading about content based image search.

Also, LTU presentations from the 2003 and 2004 Search Engine Meeting provide excellent intros to CBIR:

+ Organising personal pictures with content analysis technology
From the 2004 meeting. PDF file.

+ Finding the Right Image in the Corbis Collection
From the 2003 meeting. PDF file.

ClickZ Live Toronto Twitter Canada MD Kirstine Stewart to Keynote Toronto
ClickZ Live Toronto (May 14-16) is a new event addressing the rapidly changing landscape that digital marketers face. The agenda focuses on customer engagement and attaining maximum ROI through online marketing efforts across paid, owned & earned media. Register now and save!*
*Early Bird Rates expire April 17.

Recommend this story

comments powered by Disqus