Image retrieval

An image retrieval system is a computer system for browsing, searching and retrieving images from a large database of digital images. Most traditional and common methods of image retrieval utilize some method of adding metadata such as captioning, keywords, or descriptions to the images so that retrieval can be performed over the annotation words. Manual image annotation is time-consuming, laborious and expensive; to address this, there has been a large amount of research done on automatic image annotation. Additionally, the increase in social web applications and the semantic web have inspired the development of several web-based image annotation tools.

The first microcomputer-based image database retrieval system was developed at MIT, in the 1980s, by Banireddy Prasad, Amar Gupta, Hoo-min Toong, and Stuart Madnick. [Cite journal
volume = IE-34
issue = 1
pages = 83–8
last = Prasad
first = B E
coauthors = A Gupta, H-M Toong, S.E. Madnick
title = A microcomputer-based image database management system
doi=10.1109/TIE.1987.350929
journal = IEEE Transactions on Industrial Electronics
year = 1987
month = February]

Another method of image retrieval is content-based image retrieval (CBIR), which aims at avoiding the use of textual descriptions and instead retrieves images based on their visual similarity to a user-supplied query image or user-specified image features.

Evaluations

There are evaluation workshops for image retrieval systems aiming to investigate and improve the performance of such systems.
* [http://www.imageclef.org ImageCLEF] - a continuing track of the [http://www.clef-campaign.org Cross Language Evaluation Forum] that evaluates systems using both textual and pure-image retrieval methods.
* [http://ieeexplore.ieee.org/xpl/RecentCon.jsp?punumber=4980 Content-based Access of Image and Video Libraries] - a series of IEEE workshops from 1998 to 2001.

ee also

*Computer vision
*Digital asset management
*Digital image editing
*Information retrieval
*Image processing

References

External links

* [http://www.alipr.com alipr.com] Automatic image tagging and visual image search. Developed with Stanford and Penn State technologies.

* [http://amazon.ece.utexas.edu/~qasim/research.htm CIRES] Image retrieval system developed by the University of Texas at Austin.

* [http://thomas.deselaers.de/FIRE FIRE] Image retrieval system developed by the RWTH Aachen University, Aachen, Germany.

* [http://www.gnu.org/software/gift/ GIFT] GNU Image Finding Tool, originally developed at the University of Geneva, Switzerland.

* [http://ieeexplore.ieee.org/xpl/RecentCon.jsp?punumber=7767&conhome=6885 IEEE CBAIVL Proceedings]

* [http://www.imageclef.org ImageCLEF] A benchmark to compare the performance of image retrieval systems.

* [http://www.imgseek.net imgSeek] Open-source desktop photo collection manager and viewer with content-based search and many other features.

* [http://www.anaktisi.net img(Anaktisi)] This Web-Solution implements a new family of CBIR descriptors. These descriptors combine in one histogram color and texture information and are suitable for accurately retrieving images.

* [http://www.semanticmetadata.net/ Caliph & Emir] : Creation and Retrieval of images based on MPEG-7 (GPL).

* [http://www.img-rummager.com img(Rummager)] : Image retrieval Engine (Freeware Applicaton).