COLOR BLOBS-BASED IMAGE RETRIEVAL IN BROAD DOMAINS
|
Accession number;05A0212957
|
| Title;COLOR BLOBS-BASED IMAGE RETRIEVAL IN BROAD DOMAINS |
| Author;
GAVILAN D
(Tokyo Inst. Technol., Meguro-ku, Jpn)
TAKAHASHI H
(Tokyo Inst. Technol., Meguro-ku, Jpn)
NAKAJIMA M
(Tokyo Inst. Technol., Meguro-ku, Jpn)
|
Journal Title;IEIC Technical Report (Institute of Electronics, Information and Communication Engineers)
|
Journal Code:S0532B
|
ISSN:0913-5685
|
|
VOL.104;NO.544(IE2004 124-144);PAGE.43-48(2005)
|
| Figure&Table&Reference;FIG.9, TBL.1, REF.12 |
| Pub. Country;Japan |
| Language;English |
| Abstract;In this paper, we propose a new method for Image Retrieval using Color Blobs. These blobs are regions found using a Neural Network-based color quantization over the Scale Space of the images. The features of each blob are then used to index images in a database. Furthermore, we add other commodity searches to the system, such as the annotation generated automatically using image categorization, physical location context using GPS, or color exclusion search. The method is compared with methods based on Color Histograms, showing the increase in speed, recall and precision. We also show how our method is compatible with other approaches in combined queries. (author abst.) |
|
|
|
Related Articles;
|
|
