International Journal of Computer Vision

, Volume 72, Issue 2, pp 133–157

Semantic Modeling of Natural Scenes for Content-Based Image Retrieval

Article

DOI: 10.1007/s11263-006-8614-1

Cite this article as:
Vogel, J. & Schiele, B. Int J Comput Vision (2007) 72: 133. doi:10.1007/s11263-006-8614-1

Abstract

In this paper, we present a novel image representation that renders it possible to access natural scenes by local semantic description. Our work is motivated by the continuing effort in content-based image retrieval to extract and to model the semantic content of images. The basic idea of the semantic modeling is to classify local image regions into semantic concept classes such as water, rocks, or foliage. Images are represented through the frequency of occurrence of these local concepts. Through extensive experiments, we demonstrate that the image representation is well suited for modeling the semantic content of heterogenous scene categories, and thus for categorization and retrieval.

The image representation also allows us to rank natural scenes according to their semantic similarity relative to certain scene categories. Based on human ranking data, we learn a perceptually plausible distance measure that leads to a high correlation between the human and the automatically obtained typicality ranking. This result is especially valuable for content-based image retrieval where the goal is to present retrieval results in descending semantic similarity from the query.

Keywords

semantic scene understandingcontent-based image retrievalscene clasificationhuman scene preceptionperceptually based techniquescomputer vision

Copyright information

© Springer Science + Business Media, LLC 2006

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of British ColumbiaVancouverCanada
  2. 2.Computer Science DepartmentDarmstadt University of TechnologyGermany