DocumentCode :
2214655
Title :
Semantic image retrieval and auto-annotation by converting keyword space to image space
Author :
Celebi, Erbug ; Alpkocak, Adil
Author_Institution :
Dept. of Comput. Eng., Dokuz Eylul Univ., Izmir
fYear :
0
fDate :
0-0 0
Abstract :
In this paper, we propose a novel strategy at an abstract level by combining textual and visual clustering results to retrieve images using semantic keywords and auto-annotate images based on similarity with existing keywords. Our main hypothesis is that images that fall in to the same text-cluster can be described with common visual features of those images. In order to implement this hypothesis, we set out to estimate the common visual features in the textually clustered images. When given an un-annotated image, we find the best image match in the different textual clusters by processing their low-level features. Experiments have demonstrated that good accuracy of proposal and its high potential use in annotation of images and for improvement of content based image retrieval
Keywords :
content-based retrieval; image retrieval; pattern clustering; auto-annotation; content based image retrieval; image space; keyword space; semantic image retrieval; semantic keyword; textual clustering; textually clustered image; visual clustering; Content based retrieval; Disaster management; Image converters; Image recognition; Image retrieval; Image segmentation; Information retrieval; Internet; Proposals; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multi-Media Modelling Conference Proceedings, 2006 12th International
Conference_Location :
Beijing
Print_ISBN :
1-4244-0028-7
Type :
conf
DOI :
10.1109/MMMC.2006.1651315
Filename :
1651315
Link To Document :
بازگشت