Title :
Large image database retrieval based on texture features
Author :
Grgic, Mislav ; Grgic, Sonja ; Ghanbari, Mohammed
Author_Institution :
Dept. of Radiocommun., Zagreb Univ., Croatia
Abstract :
In recent years, there has been a growing interest in developing effective methods for searching large image databases based on image content. The interest in image search algorithms has grown out of the necessity of managing large image databases that are now commonly available on removable storage media and wide area networks. The objective of this paper is to present a novel image retrieval system based on texture features extraction. The system works with the subdatabases that include images with the same content. Subdatabases are described with centroids. Comparison with conventional retrieval systems show that new system is faster and more accurate.
Keywords :
feature extraction; image retrieval; image texture; visual databases; centroids; image database management; image database retrieval system; image search algorithms; storage media; subdatabases; texture feature extraction; wide area networks; Computer network management; Electronic mail; Feature extraction; Head; Image databases; Image retrieval; Image storage; Information retrieval; Multimedia databases; Spatial databases;
Conference_Titel :
Industrial Technology, 2003 IEEE International Conference on
Print_ISBN :
0-7803-7852-0
DOI :
10.1109/ICIT.2003.1290790