An intelligent image retrieval system based on the synergy of color and artificial ant colonies

Authors:
Konstantinos Konstantinidis;Georgios Ch. Sirakoulis;Ioannis Andreadis
Affiliations:
Laboratory of Electronics, Dept. of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece;Laboratory of Electronics, Dept. of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece;Laboratory of Electronics, Dept. of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece
Venue:
SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis
Year:
2007

Citing 5
Cited 1

Color indexing

International Journal of Computer Vision
Comparing images using joint histograms

Multimedia Systems - Special issue on video content based retrieval
Visual information retrieval

Visual information retrieval
Performance evaluation in content-based image retrieval: overview and proposals

Pattern Recognition Letters - Special issue on image/video indexing and retrieval
Ant system: optimization by a colony of cooperating agents

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Design and implementation of a fuzzy-modified ant colony hardware structure for image retrieval

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a new image retrieval algorithm is proposed which aims to discard irrelevant images and increase the amount of relevant ones in a large database. This method utilizes a two-stage ant colony algorithm employing in parallel color, texture and spatial information. In the first stage, the synergy of the low-level descriptors is considered to be a group of ants seeking the optimal path to the "food" which is the most similar image to the query, whilst settling pheromone on each of the images that they confront in the high similarity zone. In the second stage additional queries are made by using the highest ranked images as new queries, resulting in an aggregate deposition of pheromone through which the final retrieval is performed. The results prove the system to be satisfactorily efficient as well as fast.