Noise-Robust Detection of Symmetric Axes by Self-Correcting Artificial Neural Network

详细信息    查看全文

• 作者：Wonil Chang ; Hyun Ah Song ; Sang-Hoon Oh ; Soo-Young Lee
• 关键词：Symmetry axis detection ; Asymmetry correction ; Oscillator network ; Directional blurring filter
• 刊名：Neural Processing Letters
• 出版年：2015
• 出版时间：April 2015
• 年：2015
• 卷：41
• 期：2
• 页码：179-189
• 全文大小：1,053 KB
• 参考文献：1. Beck J, Hope B, Rosenfeld A (1983) (U.S.), N.S.F.: Human and machine vision. Academic Press
  2. Chertok, M, Keller, Y (2010) Spectral symmetry analysis. IEEE Trans Pattern Anal Mach Intell 32: pp. 1227-1238 CrossRef
  3. Cho M, Lee KM (2009) Bilateral symmetry detection via symmetry-growing. In: Proceedings of the British machine vision conference
  4. Dakin, S, Watt, R (1994) Detection of bilateral symmetry using spatial filters. Spat Vis 8: pp. 393-413 CrossRef
  5. Enquist, M, Arak, A (1994) Symmetry, beauty and evolution. Nature 372: pp. 169-172 CrossRef
  6. Frintrop, S, Rome, E, Christensen, HI (2010) Computational visual attention systems and their cognitive foundations: A survey. ACM Trans Appl Percept 7: pp. 6 CrossRef
  7. Fukushima, K (2005) Use of non-uniform spatial blur for image comparison: symmetry axis extraction. Neural Netw 18: pp. 23-32 CrossRef
  8. Jeong, S, Ban, SW, Lee, M (2008) Stereo saliency map considering affective factors and selective motion analysis in a dynamic environment. Neural netw 21: pp. 1420-1430 CrossRef
  9. Kootstra G, Nederveen A, De Boer B (2008) Paying attention to symmetry. In: Proceedings of the British Machine Vision Conference (BMVC2008), pp 1115-125. The British Machine Vision Association and Society for Pattern Recognition
  10. Lazebnik S, Schmid C, Ponce J., et al. (2004) Semi-local affine parts for object recognition. In: British Machine Vision Conference (BMVC-4), pp 779-88
  11. Lee, S, Liu, Y (2010) Skewed rotation symmetry group detection. IEEE Trans Pattern Anal Mach Intell 32: pp. 1659-1672 CrossRef
  12. Lee, S, Liu, Y (2012) Curved glide-reflection symmetry detection. IEEE Trans Pattern Anal Mach Intell 34: pp. 266-278 CrossRef
  13. Lowe, DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60: pp. 91-110 CrossRef
  14. Loy G, Eklundh JO (2006) Detecting symmetry and symmetric constellations of features. In: European Conference on Computer Vision (ECCV2006), pp 508-21. Springer
  15. Machilsen, B, Pauwels, M, Wagemans, J (2009) The role of vertical mirror symmetry in visual shape detection. J Vis 9: pp. 1-11 CrossRef
  16. Mikolajczyk, K, Schmid, C (2004) Scale & affine invariant interest point detectors. Int J Comput Vis 60: pp. 63-86 CrossRef
  17. Osorio D (1996) Symmetry detection by categorization of spatial phase, a model. Proceedings of the Royal Society of London. Series B: Biological Sciences 263(1366):105-10
  18. Park M, Brocklehurst K, Collins RT, Liu Y (2010) Translation-symmetry-based perceptual grouping with applications to urban scenes. In: Asian Conference on Computer Vision (ACCV2010), pp 329-42. Springer
  19. Poirier, FJ, Wilson, HR (2006) A biologically plausible model of human radial frequency perception. Vision Res 46: pp. 2443-2455 CrossRef
  20. Poirier, FJ, Wilson, HR (2010) A biologically plausible model of human shape symmetry perception. J Vis 10: pp. 1-16
  21. Reisfeld, D, Wolfson, H, Yeshurun, Y (1995) Context-free attentional operators: the generalized symmetry transform. Int J Comput Vis 14: pp. 119-130 CrossRef
  22. Temlyakov A, Munsell BC, Waggoner JW, Wang S (2010) Two perceptually motivated strategies for shape classification. In: Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pp 2289-296. IEEE
  23. Treder, MS (2010) Behind the
• 刊物类别：Physics and Astronomy
• 刊物主题：Physics
  Complexity
  Artificial Intelligence and Robotics
  Electronic and Computer Engineering
  Operation Research and Decision Theory
  
• 出版者：Springer Netherlands
• ISSN：1573-773X

文摘

Perception of symmetric image patterns is one of the important stages in visual information processing. However, local interference of the input image disturbs the detection of symmetry in artificial neural network based models. In this paper, we propose a noise-robust neural network model that can correct asymmetric corruptions and returns clear symmetry axes. For efficient detection of bilateral symmetry as well as asymmetry correction, our network adopts directional blurring filters. The filter responses are fed to oscillatory neurons for line extraction, which serializes the activation of multiple symmetry axes. Given an activated symmetry axis, the network estimates the difference of counterparts to generate a masking filter that covers the asymmetric parts. The network reconstructs the ideal mirror-symmetric image with complete symmetry axes by self-correction of corruptions. Through simulations on corrupted images, we verify that our network is superior to Fukushima’s symmetry detection network. Our network successfully presents biologically plausible and robust symmetry perception mechanism.