Abstract
In this paper, we propose a symmetry axis detection network that can correct asymmetric parts by itself. Our network compares directional blurring of omnidirectional image edges, which plays a significant role in asymmetry detection and correction. The output layer consists of oscillatory neurons, which activates symmetry axes one by one. Given activated symmetry axis, network estimates the difference of image edges and generates a masking filter to cover the asymmetric parts. The network reconstructs ideal mirror-symmetric image with complete symmetry axes by self-correction. Our network models flexible symmetry perception of high-level cognitive function of human brain.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Treder, M.S.: Behind the Looking-Glass: A Review on Human Symmetry Perception. Symmetry 2, 1510–1543 (2010)
Wang, W., Gao, Y., Hui, S.C., Leung, M.K.: A Fast and Robust Algorithms for Face Detection and Localization. In: Proceedings of the 9th International Conference on Neural Information Processing, pp. 2118–2121. IEEE Press (2002)
Palmer, S.E.: Human and Machine Vision. Academic Press, USA (1983)
Graham, N.V.S.: Visual Pattern Analyzers, Oxford, UK (1989)
Fukushima, K., Kikuchi, M.: Symmetry Axis Extraction by a Neural Network. Neurocomputing 69, 1827–1836 (2006)
Wang, D.L., Terman, D.: Image Segmentation Based on Oscillatory Correlation. Neural Computation 9, 805–836 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chang, W., Song, H.A., Oh, SH., Lee, SY. (2012). Self-correcting Symmetry Detection Network. In: Huang, T., Zeng, Z., Li, C., Leung, C.S. (eds) Neural Information Processing. ICONIP 2012. Lecture Notes in Computer Science, vol 7664. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34481-7_68
Download citation
DOI: https://doi.org/10.1007/978-3-642-34481-7_68
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34480-0
Online ISBN: 978-3-642-34481-7
eBook Packages: Computer ScienceComputer Science (R0)