Universität Augsburg Towards Universal Visual Vocabularies

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. Keywords— visual vocabulary, visual words, image classification