TY - GEN
T1 - Categorization of natural scenes
T2 - 3rd Symposium on Applied Perception in Graphics and Visualization, APGV 2006
AU - Vogel, Julia
AU - Schwaninger, Adrian
AU - Wallraven, Christian
AU - Bülthoff, Heinrich H.
PY - 2006
Y1 - 2006
N2 - 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.
AB - 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.
KW - Computational modeling
KW - Gist
KW - Global configural information
KW - Local region-based information
KW - Scene classification
KW - Scene perception
KW - Semantic modeling
UR - http://www.scopus.com/inward/record.url?scp=85032070812&partnerID=8YFLogxK
U2 - 10.1145/1140491.1140498
DO - 10.1145/1140491.1140498
M3 - Conference contribution
AN - SCOPUS:85032070812
SN - 1595934294
SN - 9781595934291
T3 - Proceedings - APGV 2006: Symposium on Applied Perception in Graphics and Visualization
SP - 33
EP - 40
BT - Proceedings - APGV 2006
PB - Association for Computing Machinery (ACM)
Y2 - 28 July 2006 through 29 July 2006
ER -