Image retrieval

From Wikipedia, the free encyclopedia

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.

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.

[edit] Evaluations

There are evaluation workshops for image retrieval systems that aim to investigate and improve the performance of such systems.

• ImageCLEF - a continuing track of the Cross Language Evaluation Forum (CLEF) that evaluates systems using both textual and pure-image retrieval methods.
• IEEE Content-based Access of Image and Video Libraries - a series of workshops from 1998 to 2001.

[edit] See also

• Content-based image retrieval
• Automatic image annotation
• Digital image editing
• Information retrieval
• Image processing
• Computer vision

[edit] External links

• FIRE Image retrieval system developed by the RWTH Aachen University, Aachen, Germany
• CIRES Image retrieval system developed by the University of Texas at Austin.
• ImageCLEF
• IEEE CBAIVL Proceedings