Linking images and keywords for semantics-based image retrieval

Authors:
A. Kutics;A. Nakagawa;K. Tanaka;M. Yamada;Y. Sanbe;S. Ohtsuka
Affiliations:
NTT Data Corp., Tokyo, Japan;NTT Data Corp., Tokyo, Japan;NTT Data Corp., Tokyo, Japan;NTT Data Corp., Tokyo, Japan;NTT Data Corp., Tokyo, Japan;NTT Data Corp., Tokyo, Japan
Venue:
ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 2
Year:
2003

Citing 7
Cited 2

Scale-Space and Edge Detection Using Anisotropic Diffusion

IEEE Transactions on Pattern Analysis and Machine Intelligence
Content-Based Image Retrieval at the End of the Early Years

IEEE Transactions on Pattern Analysis and Machine Intelligence
Exploiting image semantics for picture libraries

Proceedings of the 1st ACM/IEEE-CS joint conference on Digital libraries
Modern Information Retrieval

Modern Information Retrieval
Unifying Keywords and Visual Contents in Image Retrieval

IEEE MultiMedia
Learning-based linguistic indexing of pictures with 2--d MHMMs

Proceedings of the tenth ACM international conference on Multimedia
Combining Textual and Visual Cues for Content-Based Image Retrieval on the World Wide Web

CBAIVL '98 Proceedings of the IEEE Workshop on Content - Based Access of Image and Video Libraries

Using dual cascading learning frameworks for image indexing

VIP '05 Proceedings of the Pan-Sydney area workshop on Visual information processing
Discovering recurrent image semantics from class discrimination

EURASIP Journal on Applied Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

One of the major problems with existing content-based image retrieval systems is that their objective similarity can rarely match the user's subjective and context-dependent similarity interpretation. We propose a novel approach to linking images and textual information to overcome this problem. First, salient image objects and also their structural and visual features are extracted. Next, keywords and images are linked in two stages: (1) by mapping low-level visual features of objects to related words using feature lexicons, and (2) by assigning words expressing higher-level semantic concepts to images on the basis of the feature-related words, lexical definitions, and the user's relevance feedback. Experimental results show that the user's retrieval semantics can be approximated better via this two-level multi-modality and also by supporting a large variety of querying and browsing schemes and thus higher-level interactivity.