Towards Universal Visual Vocabularies

C. Ries, S. Romberg, R. Lienhart

TOWARDS UNIVERSAL VISUAL VOCABULARIES

2010-05

erschienen 01.07.10 Technical Report, Institute of Computer Science, University of Augsburg,

ABSTRACT

Many content-based image mining systems extract local features

from images to obtain an image description based on discrete

feature occurrences. Such applications require a visual

vocabulary also known as visual codebook or visual dictionary

to discretize the extracted high-dimensional features to visual

words in an efficient yet accurate way.

Once such an application operates on images of a very specific

domain the question arises if a vocabulary built from those

domain-specific images needs to be used or if a ”universal” visual

vocabulary can be used instead. A universal visual vocabulary

may be computed from images of a different domain once

and then be re-used for various applications and other domains.

We therefore evaluate several visual vocabularies from different

image domains by determining their performance at

pLSA-based image classification on several datasets. We empirically

conclude that vocabularies suit our classification tasks

equally well disregarding the image domain they were derived

from.