Abstract
Symmetry has long been considered as an influential Gestalt factor for grouping and figure-ground segregation. As natural contours are not precisely symmetric in terms of geometry, we proposed a quantification of the degree of symmetry (DoS) that is applicable for arbitrary contours in natural images. DoS showed an agreement with the perception of symmetry in judgment of symmetry axis. Multi-dimensional scaling, together with similarity tests among natural contours, showed that DoS is a quantitative perceptual measure that accounts for the shape of contour. These results indicate that DoS reflects the perception of symmetry in natural contours, and further suggest that DoS is a plausible candidate for representing shape in the cortex.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Hung, C.C., Carlson, E.T., Connor, C.E.: Medial axis shape cording in Macaque inferotemporal cortex. Neuron 74, 1099–1113 (2012)
Hatori, Y., Sakai, K.: Early representation of shape by onset synchronization of border-ownership-selective cells in the V1-V2 network. J. Opt. Soc. Am., A 31, 716–729
Gheorghiu, E., Bell, J., Kingdom, F.A.A.: Visual adaptation to symmetry. VSS 2014 23, 227 (2014)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measureing ecological statistics. Proc. ICCV 2, 416–423 (2001)
Kruscal, J.B.: Multidimensional scaling by optimizing goodness of fit to a non-metric hypothesis. Psychometrika 29, 1–27 (1964)
Fowlkes, C.C., Martin, D.R., Malik, J.: Local figure-ground cues are valid for natural images. J. Vision 7(8), 2 (2007), doi:10.1167/7.8.2
Sakai, K., Nishimura, H., Shimizu, R., Kondo, K.: Consistent and robust determination of border ownership based on asymmetric surrounding contrast. Neural Networks 33, 257–274 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Sakai, K., Kurematsu, K., Matsuoka, S. (2014). Perception of Symmetry in Natural Images. In: Loo, C.K., Yap, K.S., Wong, K.W., Beng Jin, A.T., Huang, K. (eds) Neural Information Processing. ICONIP 2014. Lecture Notes in Computer Science, vol 8836. Springer, Cham. https://doi.org/10.1007/978-3-319-12643-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-12643-2_17
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12642-5
Online ISBN: 978-3-319-12643-2
eBook Packages: Computer ScienceComputer Science (R0)