Categorization of natural scenes: Local vs. global information

Julia Vogel, Adrian Schwaninger, Christian Wallraven, Heinrich Bulthoff

Research output: Chapter in Book/Report/Conference proceedingConference contribution

30 Citations (Scopus)


Understanding the robustness and rapidness of human scene categorization has been a focus of investigation in the cognitive sciences over the last decades. At the same time, progress in the area of image understanding has prompted computer vision researchers to design computational systems that are capable of automatic scene categorization. Despite these efforts, a framework describing the processes underlying human scene categorization that would enable efficient computer vision systems is still missing. In this study, we present both psychophysical and computational experiments that aim to make a further step in this direction by investigating the processing of local and global information in scene categorization. In a set of human experiments, categorization performance is tested when only local or only global image information is present. Our results suggest that humans rely on local, region-based information as much as on global, configural information. In addition, humans seem to integrate both types of information for intact scene categorization. In a set of computational experiments, human performance is compared to two state-of-the-art computer vision approaches that model either local or global information.

Original languageEnglish
Title of host publicationProceedings - APGV 2006
Subtitle of host publicationSymposium on Applied Perception in Graphics and Visualization
PublisherAssociation for Computing Machinery (ACM)
Number of pages8
ISBN (Print)1595934294, 9781595934291
Publication statusPublished - 2006
Externally publishedYes
Event3rd Symposium on Applied Perception in Graphics and Visualization, APGV 2006 - Boston, MA, United States
Duration: 2006 Jul 282006 Jul 29


Other3rd Symposium on Applied Perception in Graphics and Visualization, APGV 2006
Country/TerritoryUnited States
CityBoston, MA


  • Computational modeling
  • Gist
  • Global configural information
  • Local region-based information
  • Scene classification
  • Scene perception
  • Semantic modeling

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Software


Dive into the research topics of 'Categorization of natural scenes: Local vs. global information'. Together they form a unique fingerprint.

Cite this