CIRES: Content Based Image REtrieval System
CIRES is a robust content-based image retrieval system based upon a combination of higher-level and lower-level vision principles. Higher-level analysis uses perceptual organization, inference and grouping principles to extract semantic information describing the structural content of an image. Lower-level analysis employs a channel energy model to describe image texture, and utilizes color histogram techniques. Gabor filters are used to extract fractional energies in various spatial-frequency channels. The system is able to serve queries ranging from scenes of purely natural objects such as vegetation, trees, sky, etc. to images containing conspicuous structural objects such as buildings, towers, bridges, etc.
To view some sample
queries and the corresponding first few most similar
images retrieved, please click here.
Images have been divided into various classes and subclasses for users' convenience and research. Otherwise, CIRES searches the whole image database to retrieve the best matches for any particular image query.
Update (August 2007)
Query CIRES with any image you wish
, and browse our updated image library of over 57,000 images on the new CIRES website: http://cires.matthewriley.com
Relevance feedback using:
For more details:
- Cluster queries
- Multi-class classification
Feature Integration, Multi-image Queries, and Relevance Feedback in Image Retrieval