Title :
Visual word pairs for automatic image annotation
Author :
Herve, Nicolas ; Boujemaa, Nozha
Author_Institution :
IMEDIA project Domaine de Voluceau, INRIA Paris-Rocquencourt, Le Chesnay, France
fDate :
June 28 2009-July 3 2009
Abstract :
The bag-of-visual-words is a popular representation for images that has proven to be quite effective for automatic annotation. In this paper, we extend this representation in order to include weak geometrical information by using visual word pairs. We show on a standard benchmark dataset that this new image representation improves significantly the performances of an automatic annotation system.
Keywords :
image representation; text analysis; automatic image annotation; image representation; standard benchmark dataset; visual word pairs; weak geometrical information; Histograms; Image databases; Image representation; Labeling; Layout; Object detection; Performance evaluation; Support vector machines; Visual databases; Vocabulary; bag-of-visual-words; co-occurence; image annotation; support vector machine (SVM); visual vocabulary; visual word pairs;
Conference_Titel :
Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on
Conference_Location :
New York, NY
Print_ISBN :
978-1-4244-4290-4
Electronic_ISBN :
1945-7871
DOI :
10.1109/ICME.2009.5202526
