Visual Word Ambiguity

8 years 9 months ago
Visual Word Ambiguity
— This paper studies automatic image classification by modeling soft-assignment in the popular codebook model. The codebook model describes an image as a bag of discrete visual words selected from a vocabulary, where the frequency distributions of visual words in an image allow classification. One inherent component of the codebook model is the assignment of discrete visual words to continuous image features. Despite the clear mismatch of this hard assignment with the nature of continuous features, the approach has been applied successfully for some years. In this paper we investigate four types of soft-assignment of visual words to image features. We demonstrate that explicitly modeling visual word assignment ambiguity improves classification performance compared to the hard-assignment of the traditional codebook model. The traditional codebook model is compared against our method for five well-known datasets: 15 natural scenes, Caltech-101, Caltech256, and Pascal VOC 2007/2008....
Jan van Gemert, Cor J. Veenman, Arnold W. M. Smeul
Added 29 Jan 2011
Updated 29 Jan 2011
Type Journal
Year 2010
Where PAMI
Authors Jan van Gemert, Cor J. Veenman, Arnold W. M. Smeulders, Jan-Mark Geusebroek
Comments (0)