Advertisement

International Journal of Automation and Computing

, Volume 15, Issue 6, pp 656–672 | Cite as

An Overview of Contour Detection Approaches

  • Xin-Yi Gong
  • Hu Su
  • De Xu
  • Zheng-Tao Zhang
  • Fei Shen
  • Hua-Bin YangEmail author
Review

Abstract

Object contour plays an important role in fields such as semantic segmentation and image classification. However, the extraction of contour is a difficult task, especially when the contour is incomplete or unclosed. In this paper, the existing contour detection approaches are reviewed and roughly divided into three categories: pixel-based, edge-based, and region-based. In addition, since the traditional contour detection approaches have achieved a high degree of sophistication, the deep convolutional neural networks (DCNNs) have good performance in image recognition, therefore, the DCNNs based contour detection approaches are also covered in this paper. Moreover, the future development of contour detection is analyzed and predicted.

Keywords

Contour detection contour salience gestalt principle contour grouping active contour 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

Acknowledgements

This work was supported by National Natural Science Foundation of China (Nos. 61503378, 61473293, 51405485 and 61403378), the Project of Development in Tianjin for Scientific Research Institutes, and Tianjin Government (No. 16PTYJGX00050).

References

  1. [1]
    G. Papari, N. Petkov. Edge and line oriented contour detection: State of the art. Image and Vision Computing, vol. 29, no.2–3, pp. 79–103, 2011. DOI:  https://doi.org/10.1016/j.imavis.2010.08.009.Google Scholar
  2. [2]
    Y. S. Ming, H. D. Li, X. M. He. Contour completionwithout region segmentation. IEEE Transactions on Image Processing, vol. 25, no. 9, pp. 3597–3611, 2016. DOI:  https://doi.org/10.1109/TIP.2016.2564646.MathSciNetGoogle Scholar
  3. [3]
    D. Ziou, S. Tabbone. Edge detection techniques-an overview. Pattern Recognition & Image Analysis, vol. 8, no.4, pp. 537–559, 1998.Google Scholar
  4. [4]
    D. R. Martin, C. C. Fowlkes, J. Malik. Learning to detectnatural image boundaries using local brightness, color,and texture cues. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 5, pp. 530–549, 2004. DOI:  https://doi.org/10.1109/TPAMI.2004.1273918.Google Scholar
  5. [5]
    P. Arbelaez, M. Maire, C. Fowlkes, J. Malik. Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 5, pp. 898–916, 2011. DOI:  https://doi.org/10.1109/TPAMI.2010.161.Google Scholar
  6. [6]
    Y. LeCun, Y. Bengio, G. Hinton. Deep learning. Nature, vol. 521, no. 7553, pp. 436–444, 2015. DOI:  https://doi.org/10.1038/nature14539.Google Scholar
  7. [7]
    J. M. Yang, B. Price, S. Cohen, H. Lee, M. H. Yang. Object contour detection with a fully convolutional encoder-decoder network. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, pp. 193–202, 2016. DOI:  https://doi.org/10.1038/nature1453910.1109/CVPR.2016.28.Google Scholar
  8. [8]
    M. S. Nixon, A. S. Aguado..Feature Extraction & Image Processing for Computer Vision, 3rd ed., Amsterdam, Holland: Elsevier, 2012.Google Scholar
  9. [9]
    J. Canny. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679–698, 1986. DOI:  https://doi.org/10.1038/nature1453910.1109/TPAMI.1986.4767851.Google Scholar
  10. [10]
    X. Wang. Laplacian operator-based edge detectors. IEEETransactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 5, pp. 886–890, 2007. DOI:  https://doi.org/10.1109/TPAMI.2007.1027.Google Scholar
  11. [11]
    P. Perona, J. Malik. Detecting and localizing edges composed of steps, peaks and roofs. In Proceedings of the 3rdInternational Conference on Computer Vision, IEEE,Osaka, Japan, pp. 52–57, 1990. DOI:  https://doi.org/10.1109/ICCV.1990.139492.Google Scholar
  12. [12]
    Y. Lu, R. C. Jain. Reasoning about edges in scale space. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 4, pp. 450–468, 1992. DOI:  https://doi.org/10.1109/34.126806.Google Scholar
  13. [13]
    P. Perona, J. Malik. Scale-space and edge detection usinganisotropic diffusion. IEEE Transactions on PatternAnalysis and Machine Intelligence, vol. 12, no. 7, pp. 629–639, 1990. DOI:  https://doi.org/10.1109/34.56205.Google Scholar
  14. [14]
    J. Malik, S. Belongile, T. Leung, J. B. Shi. Contour andtexture analysis for image segmentation. InternationalJournal of Computer Vision, vol. 43, no. 1, pp. 7–27, 2001. DOI:  https://doi.org/10.1023/A:1011174803800.Google Scholar
  15. [15]
    N. Petkov, M. A. Westenberg. Suppression of contourperception by band-limited noise and its relation to non-classical receptive field inhibition. Biological Cybernetics, vol. 88, no. 3, pp. 236–246, 2003. DOI:  https://doi.org/10.1007/s00422-002-0378-2 zbMATHGoogle Scholar
  16. [16]
    D. J. Field, A. Hayes, R. F. Hess. Contour integration bythe human visual system: Evidence for a local “association field”. Vision Research, vol. 33, no. 2, pp. 173–193, 1993. DOI:  https://doi.org/10.1016/0042-6989(93)90156-Q.Google Scholar
  17. [17]
    D. H. Hubel, T. N. Wiesel. Receptive fields and functional architecture of monkey striate cortex. The Journal ofPhysiology, vol. 195, no. 1, pp. 215–243, 1968. DOI:  https://doi.org/10.1113/jphysiol.1968.sp008455.Google Scholar
  18. [18]
    H. E. Jones, K. L. Grieve, W. Wang, A. M. Sillito. Surround suppression in primate V1. Journal of Neurophysiology, vol. 86, no. 4, pp. 2011–2028, 2001. DOI:  https://doi.org/10.1152/jn.2001.86.4.2011.Google Scholar
  19. [19]
    P. Series, J. Lorenceau, Y. Fregnac. The “silent” surround of V1 receptive fields: Theory and experiments. Journal of Physiology-Paris, vol. 97, no. 4–6, pp. 453–474, 2003. DOI:  https://doi.org/10.1016/j.jphysparis.2004.01.023.Google Scholar
  20. [20]
    J. G. Daugman. Uncertainty relation for resolution inspace, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. Journal of the Optical Society of America A, vol. 2, no. 7, pp. 1160–1169, 1985. DOI:  https://doi.org/10.1364/JOSAA.2.001160.Google Scholar
  21. [21]
    J. P. Jones, L. A. Palmer. An evaluation of the two-dimensional Gabor filter model of simple receptive fields incat striate cortex. Journal of Neurophysiology, vol. 58, no. 6, pp. 1233–1258, 1987. DOI:  https://doi.org/10.1152/jn.1987.58.6.1233.Google Scholar
  22. [22]
    W. Chan, G. Coghill. Text analysis using local energy.Pattern Recognition, vol. 34, no. 12, pp. 2523–2532, 2001. DOI:  https://doi.org/10.1016/S0031-3203(00)00155-2.zbMATHGoogle Scholar
  23. [23]
    R. C. Zhao, M. Wu, X. Y. Liu, B. J. Zou, F. F. Li. Orientation histogram-based center-surround interaction: Anintegration approach for contour detection. Neural Computation, vol. 29, no. 1, pp. 171–193, 2017. DOI:  https://doi.org/10.1162/NECO_a_00911.Google Scholar
  24. [24]
    M. P. Sceniak, D. L. Ringach, M. J. Hawken, R. Shapley. Contrast’s effect on spatial summation by macaque V1neurons. Nature Neuroscience, vol. 2, no. 8, pp. 733–739, 1999. DOI:  https://doi.org/10.1038/11197.Google Scholar
  25. [25]
    M. P. Sceniak, M. J. Hawken, R. Shapley. Visual spatial characterization of macaque V1 neurons. Journal ofNeurophysiology, vol. 85, no. 5, pp. 1873–1887, 2001. DOI:  https://doi.org/10.1152/jn.2001.85.5.1873.Google Scholar
  26. [26]
    J. R. Cavanaugh, W. Bair, J. A. Movshon. Nature and interaction of signals from the receptive field center andsurround in macaque V1 neurons. Journal of Neurophysiology, vol. 88, no. 5, pp. 2530–2546, 2002. DOI:  https://doi.org/10.1152/jn.00692.2001.Google Scholar
  27. [27]
    C. Grigorescu, N. Petkov, M. A. Westenberg. Contour detection based on nonclassical receptive field inhibition. IEEE Transactions on Image Processing, vol. 12, no. 7, pp. 729–739, 2003. DOI:  https://doi.org/10.1109/TIP.2003.814250.Google Scholar
  28. [28]
    C. Grigorescu, N. Petkov, M. A. Westenberg. Contour and boundary detection improved by surround suppression of texture edges. Image and Vision Computing, vol. 22, no. 8, pp. 609–622, 2004. DOI:  https://doi.org/10.1016/j.imavis.2003.12.004.Google Scholar
  29. [29]
    N. Petkov, M. A. Westenberg. Suppression of contourperception by band-limited noise and its relation to non-classical receptive field inhibition. Biological Cybernetics, vol. 88, no. 3, pp. 236–246, 2003. DOI:  https://doi.org/10.1007/s00422-002-0378-2.zbMATHGoogle Scholar
  30. [30]
    G. Papari, N. Petkov. An improved model for surround suppression by steerable filters and multilevel inhibition with application to contour detection. Pattern Recognition, vol. 44, no. 9, pp. 1999–2007, 2011. DOI:  https://doi.org/10.1016/j.patcog.2010.08.013.Google Scholar
  31. [31]
    G. Papari, P. Campisi, N. Petkov, A. Neri. A biologically motivated multiresolution approach to contour detection.EURASIP Journal on Advances in Signal Processing, vol. 2007, Article number 071828, 2007. DOI:  https://doi.org/10.1155/2007/71828.
  32. [32]
    M. Ursino, G. E. La Cara. A model of contextual interactions and contour detection in primary visual cortex. Neural Networks, vol. 17, no.5–6, pp. 719–735, 2004. DOI:  https://doi.org/10.1016/j.neunet.2004.03.007.zbMATHGoogle Scholar
  33. [33]
    L. Long, Y. J. Li. Contour detection based on the property of orientation selective inhibition of non-classical receptive field. In Proceedings of IEEE Conference on Cybernetics and Intelligent Systems, IEEE, Chengdu, China, pp. 1002–1006, 2008. DOI:  https://doi.org/10.1109/ICCIS.2008.4670920.Google Scholar
  34. [34]
    C. Zeng, Y. J. Li, C. Y. Li. Center-surround interaction with adaptive inhibition: A computational model for contour detection. NeuroImage, vol. 55, no. 1, pp. 49–66, 2011. DOI:  https://doi.org/10.1016/j.neuroimage.2010.11.067.Google Scholar
  35. [35]
    K. F. Yang, S. B. Gao, C. F. Guo, C. Y. Li, Y. J. Li. Boundary detection using double-opponency and spatial sparseness constraint. IEEE Transactions on Image Processing, vol. 24, no. 8, pp. 2565–2578, 2015. DOI:  https://doi.org/10.1109/TIP.2015.2425538.MathSciNetGoogle Scholar
  36. [36]
    G. Azzopardi, N. Petkov. A CORF computational modelof a simple cell that relies on LGN input outperforms theGabor function model. Biological Cybernetics, vol. 106, no. 3, pp. 177–189, 2012. DOI:  https://doi.org/10.1007/s00422-012-0486-6.Google Scholar
  37. [37]
    G. Azzopardi, A. Rodriguez-Sanchez, J. Piater, N. Petkov. A push-pull CORF model of a simple cell withantiphase inhibition improves SNR and contour detection. PLoS One, vol. 9, no. 7, Article number e98424, 2014. DOI:  https://doi.org/10.1371/journal.pone.0098424.
  38. [38]
    K. F. Yang, C. Y. Li, Y. J. Li. Multifeature-based surround inhibition improves contour detection in naturalimages. IEEE Transactions on Image Processing, vol. 23, no. 12, pp. 5020–5032, 2014. DOI:  https://doi.org/10.1109/TIP.2014.2361210.MathSciNetzbMATHGoogle Scholar
  39. [39]
    U. Polat, K. Mizobe, M. W. Pettet, T. Kasamatsu, A. M. Norcia. Collinear stimuli regulate visual responses depending on cell’s contrast threshold. Nature, vol. 391, no. 6667, pp. 580–584, 1998. DOI:  https://doi.org/10.1038/35372.Google Scholar
  40. [40]
    S. C. Yen, L. H. Finkel. Extraction of perceptually salient contours by striate cortical networks. Vision Research, vol. 38, no. 5, pp. 719–741, 1998. DOI:  https://doi.org/10.1016/S0042-6989(97)00197-1.Google Scholar
  41. [41]
    T. Hansen, H. Neumann. A recurrent model of contour-integration in primary visual cortex. Journal of Vision, vol. 8, no. 8, 2008. DOI:  https://doi.org/10.1167/8.8.8.
  42. [42]
    Q. L. Tang, N. Sang, T. X. Zhang. Contour detection-based on contextual influences. Image and Vision Computing, vol. 25, no. 8, pp. 1282–1290, 2007. DOI:  https://doi.org/10.1016/j.imavis.2006.08.007.Google Scholar
  43. [43]
    Q. L. Tang, N. Sang, T. X. Zhang. Extraction of salient-contours from cluttered scenes. Pattern Recognition, vol. 40, no. 11, pp. 3100–3109, 2007. DOI:  https://doi.org/10.1016/j.pat-cog.2007.02.009.zbMATHGoogle Scholar
  44. [44]
    K. F. Yang. Computational models and applications ofthe early stages of biological visual system, Ph. D. dissertation, University of Electronic and Technology of China,China, 2016.(in Chinese)Google Scholar
  45. [45]
    N. Widynski, M. Mignotte. A particle filter framework forcontour detection. In Proceedings of the 12th EuropeanConference on Computer Vision, Springer, Florence, Italy, pp. 780–793, 2012. DOI:  https://doi.org/10.1007/978-3-642-33718-5_56.Google Scholar
  46. [46]
    N. Widynski, M. Mignotte. A MultiScale particle filter-framework for contour detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 10, pp. 1922–1935, 2014. DOI:  https://doi.org/10.1109/TPAMI.2014.2307856.Google Scholar
  47. [47]
    X. F. Ren. Multi-scale improves boundary detection in natural images. In Proceedings of the 10th European Conference on Computer Vision, Springer, Marseille, France, pp. 533–545, 2008. DOI:  https://doi.org/10.1007/978-3-540-88690-7_40.Google Scholar
  48. [48]
    X. F. Ren, L. F. Bo. Discriminatively trained sparse codegradients for contour detection. In Proceedings of the25th International Conference on Neural InformationProcessing Systems, Curran Associates Inc., Lake Tahoe, Spain, pp. 584–592, 2012.Google Scholar
  49. [49]
    P. Dollar, Z. W. Tu, S. Belongie. Supervised learning of edges and object boundaries. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, New York, USA, pp. 1964–1971, 2006. DOI:  https://doi.org/10.1109/CVPR.2006.298.Google Scholar
  50. [50]
    J. B. Shi, J. Malik. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888–905, 2000. DOI:  https://doi.org/10.1109/34.868688.Google Scholar
  51. [51]
    M. Maire, P. Arbelaez, C. Fowlkes, J. Malik. Using contours to detect and localize junctions in natural images. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Anchorage, USA, 2008. DOI:  https://doi.org/10.1109/CVPR.2008.4587420.Google Scholar
  52. [52]
    P. Arbelaez, J. Pont-Tuset, J. Barron, F. Marques, J. Malik. Multiscale combinatorial grouping. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Columbus, USA, pp. 328–335, 2014. DOI:  https://doi.org/10.1109/CVPR.2014.49.Google Scholar
  53. [53]
    J. Pont-Tuse, P. Arbelaez, J. T. Barron, F. Marques, J. Malik. Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 1, pp. 128–140, 2017. DOI:  https://doi.org/10.1109/TPAMI.2016.2537320.Google Scholar
  54. [54]
    S. Lavania, P. S. Matey. Leaf recognition using contour-based edge detection and SIFT algorithm. In Proceedngs of IEEE International Conference on Computational Intelligence and Computing Research, Coimbatore, India, pp. 1–4, 2014. DOI:  https://doi.org/10.1109/CVPR.2010.5539956.Google Scholar
  55. [55]
    Y. Lu, R. C. Jain. Behavior of edges in scale space. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 4, pp. 337–356, 1989. DOI:  https://doi.org/10.1109/34.19032.Google Scholar
  56. [56]
    T. Lindeberg. Edge detection and ridge detection with automatic scale selection. International Journal of Computer Vision, vol. 30, no. 2, pp. 117–156, 1998. DOI:  https://doi.org/10.1023/A:1008097225773.Google Scholar
  57. [57]
    S. Wang, T. Kubota, J. M. Siskind, J. Wang. Salient-closed boundary extraction with ratio contour. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 4, pp. 546–561, 2005. DOI:  https://doi.org/10.1109/TPAMI.2005.84 Google Scholar
  58. [58]
    I. J. Cox, J. M. Rehg, S. Hingorani. A Bayesian multiple-hypothesis approach to edge grouping and contour segmentation. International Journal of Computer Vision, vol. 11, no. 1, pp. 5–24, 1993. DOI:  https://doi.org/10.1007/BF01420590.Google Scholar
  59. [59]
    A. Amir, M. Lindenbaum. A generic grouping algorithm and its quantitative analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 2, pp. 168–185, 1998. DOI:  https://doi.org/10.1109/34.659934.Google Scholar
  60. [60]
    S. Mahamud, L. R. Williams, K. K. Thornber. Segmentation of multiple salient closed contours from real images. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 4, pp. 433–444, 2003. DOI:  https://doi.org/10.1109/TPAMI.2003.1190570.Google Scholar
  61. [61]
    J. H. Elder, S. W. Zucker. Computing contour closure. In Proceedings of the 4th European Conference on Computer Vision, Springer, Cambridge, UK, pp. 399–412, 1996. DOI:  https://doi.org/10.1007/BFb0015553.Google Scholar
  62. [62]
    W. S. Geisler, J. S. Perry, B. J. Super, D. P. Gallogly. Edge co-occurrence in natural images predicts contour-grouping performance. Vision Research, vol. 41, no. 6, pp. 711–724, 2001. DOI:  https://doi.org/10.1016/S0042-6989(00)00277-7.Google Scholar
  63. [63]
    K. Thornber, L. R. Williams. Analytic solution of stochastic completion fields. Biological Cybernetics, vol. 75, no. 2, pp. 141–151, 1996. DOI:  https://doi.org/10.1007/s004220050282.zbMATHGoogle Scholar
  64. [64]
    L. R. Williams, D. W. Jacobs. Stochastic completion fields: A neural model of illusory contour shape and salience. Neural Computation, vol. 9, no. 4, pp. 837–858, 1997. DOI: 10.1162/neco.1997.9.4.837.Google Scholar
  65. [65]
    A. Sha’shua, S. Ullman. Structural saliency: The detection of globally salient structures using a locally connected network. In Proceedings of the 2nd InternationalConference on Computer Vision, IEEE, Tampa, USA, 1988. DOI:  https://doi.org/10.1109/CCV.1988.590008.Google Scholar
  66. [66]
    L. Herault, R. Horaud. Figure-ground discrimination: A combinatorial optimization approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 9, pp. 899–914, 1993. DOI:  https://doi.org/10.1109/34.232076.Google Scholar
  67. [67]
    S. Sarkar, K. L. Boyer. Quantitative measures of change-based on feature organization: Eigenvalues and eigen-vectors. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, San Francisco, USA, pp. 478–483, 1996. DOI:  https://doi.org/10.1109/CVPR.1996.517115.Google Scholar
  68. [68]
    G. Guy, G. Medioni. Inferring global pereeptual contours from local features. International Journal of Computer Vision, vol. 20, no.1–2, pp. 113–133, 1996. DOI:  https://doi.org/10.1007/BF00144119.Google Scholar
  69. [69]
    L. R. Williams. A comparison of measures for detecting natural shapes in cluttered backgrounds. International Journal of Computer Vision, vol. 34, no. 2–3, pp. 81–96, 1999. DOI:  https://doi.org/10.1023/A:1008187804026.Google Scholar
  70. [70]
    I. H. Jermyn, H. Ishikawa. Globally optimal regions and boundaries as minimum ratio weight cycles. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 10, pp. 1075–1088, 2001. DOI:  https://doi.org/10.1109/34.954599.Google Scholar
  71. [71]
    T. Schoenemann, S. Masnou, D. Cremers. The elastic ratio: Introducing curvature into ratio-based image segmentation. IEEE Transactions on Image Processing, vol. 20, no. 9, pp. 2565–2581, 2011. DOI:  https://doi.org/10.1109/TIP.2011.2118225.MathSciNetzbMATHGoogle Scholar
  72. [72]
    J. S. Stahl, S. Wang. Globally optimal grouping for symmetric closed boundaries by combining boundary and region information. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, no. 3, pp. 395–411, 2008. DOI:  https://doi.org/10.1109/TPAMI.2007.1186.Google Scholar
  73. [73]
    Q. H. Zhu, G. Song, J. B. Shi. Untangling cycles for contour grouping. In Proceedings of the 11th IEEE Conference on Computer Vision, IEEE, Rio de Janeiro, Brazil, 2007. DOI:  https://doi.org/10.1109/ICCV.2007.4408929.Google Scholar
  74. [74]
    M. Meila, J. B. Shi. Learning segmentation by randomwalks. In Proceedings of the 14th Annual Neural Information Processing Systems, Denver, USA, pp. 839–873, 2001.Google Scholar
  75. [75]
    I. Kokkinos. Highly accurate boundary detection and grouping. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, San Francisco, USA, pp. 2520–2527, 2010. DOI:  https://doi.org/10.1109/CVPR.2010.5539956.Google Scholar
  76. [76]
    B. Fischer, J. M. Buhmann. Path-based clustering forgrouping of smooth curves and texture segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 4, pp. 513–518, 2003. DOI:  https://doi.org/10.1109/TPAMI.2003.1190577.Google Scholar
  77. [77]
    P. Felzenszwalb, D. McAllester. A min-cover approachfor finding salient curves. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshop, IEEE, New York, USA, pp. 185, 2006. DOI:  https://doi.org/10.1109/CVPRW.2006.18.Google Scholar
  78. [78]
    D. W. Jacobs. Robust and efficient detection of salient-convex groups. IEEE Transactions on Pattern Analysisand Machine Intelligence, vol. 18, no. 1, pp. 23–37, 1996. DOI:  https://doi.org/10.1109/34.476008.Google Scholar
  79. [79]
    Y. S. Ming, H. D. Li, X. M. He. Connected contours: A new contour completion model that respects the closureeffect. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Providence, USA, pp. 892–836, 2012. DOI:  https://doi.org/10.1109/CVPR.2012.6247755.Google Scholar
  80. [80]
    X. F. Ren, C. C. Fowlkes, J. Malik. Learning probabilistic models for contour completion in natural images. International Journal of Computer Vision, vol. 77, no. 1–3, pp. 47–63, 2008. DOI:  https://doi.org/10.1007/s11263-007-0092-6.Google Scholar
  81. [81]
    M. Kass, A. Witkin, D. Terzopoulos. Snakes: Active contour models. International Journal of Computer Vision, vol. 1, no. 4, pp. 321–331, 1988. DOI:  https://doi.org/10.1007/BF00133570.zbMATHGoogle Scholar
  82. [82]
    V. Caselles, R. Kimmel, G. Sapiro. Geodesic active contours. International Journal of Computer Vision, vol. 22, no. 1, pp. 61–79, 1997. DOI:  https://doi.org/10.1023/A:1007979827043.zbMATHGoogle Scholar
  83. [83]
    V. Caselles, R. Kimmel, G. Sapiro. Geodesic active contours. In Proceedings of International Conference on Computer Vision, IEEE, Cambridge, USA, pp. 694–699, 1995. DOI:  https://doi.org/10.1109/ICCV.1995.466871.Google Scholar
  84. [84]
    S. Kichenassamy, A. Kumar, P. Olver, A. Tannenbaum, A. Yezzi. Gradient flows and geometric active contourmodels. In Proceedings of the 5th IEEE International Conference on Computer vision, IEEE, Cambridge, USA, pp. 810–815, 1995. DOI:  https://doi.org/10.1109/ICCV.1995.466855.Google Scholar
  85. [85]
    A. Blake, M. Isard. Active Contours: The Application ofTechniques from Graphics, Vision, Control Theory andStatistics to Visual Tracking of Shapes in Motion, Berlin,Germany: Springer, pp. 49–103, 2012.Google Scholar
  86. [86]
    L. D. Cohen. On active contour models and balloons. CV-GIP: Image Understanding, vol. 53, no. 2, pp. 211–218, 1991. DOI:  https://doi.org/10.1016/1049-9660(91)90028-N.zbMATHGoogle Scholar
  87. [87]
    L. D. Cohen, L. Cohen. Finite-element methods for active contour models and balloons for 2D and 3D images. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 11, pp. 1131–1147, 1993. DOI:  https://doi.org/10.1109/34.244675.Google Scholar
  88. [88]
    C. Y. Xu, J. L. Prince. Snakes, shapes, and gradient vector flow. IEEE Transactions on Image Processing, vol. 7, no. 3, pp. 359–369, 1998. DOI:  https://doi.org/10.1109/83.661186.MathSciNetzbMATHGoogle Scholar
  89. [89]
    O. Amadieu, E. Debreuve, M. Barlaud, G. Aubert. Inward and outward curve evolution using level set method. In Proceedings of International Conference on Image Processing, IEEE, Kobe, Japan, pp. 188–192, 1999. DOI:  https://doi.org/10.1109/ICIP.1999.817097.Google Scholar
  90. [90]
    M. E. Leventon, W. E. L. Grimson, O. Faugeras. Statistical shape influence in geodesic active contours. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Hilton Head Island, USA, pp. 316–323, 2000. DOI:  https://doi.org/10.1109/CVPR.2000.855835.Google Scholar
  91. [91]
    A. Dumitras, A. N. Venetsanopoulos. Angular map-driven snakes with application to object shape description incolor images. IEEE Transactions on Image Processing, vol. 10, no. 12, pp. 1851–1859, 2001. DOI:  https://doi.org/10.1109/83.974570.zbMATHGoogle Scholar
  92. [92]
    L. H. Staib, J. S. Duncan. Boundary finding with parametrically deformable models. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 11, pp. 1061–1075, 1992. DOI:  https://doi.org/10.1109/34.166621.Google Scholar
  93. [93]
    S. R. Gunn, M. S. Nixon. A robust snake implementation:A dual active contour. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 1, pp. 63–68, 1997. DOI:  https://doi.org/10.1109/34.566812.Google Scholar
  94. [94]
    B. Al-Diri, A. Hunter, D. Steel. An active contour model for segmenting and measuring retinal vessels. IEEE Transactions on Medical imaging, vol. 28, no. 9, pp. 1488–1497, 2009. DOI:  https://doi.org/10.1109/TMI.2009.2017941.Google Scholar
  95. [95]
    J. Park, J. M. Keller. Snakes on the watershed. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 10, pp. 1201–1205, 2001. DOI:  https://doi.org/10.1109/34.954609.Google Scholar
  96. [96]
    H. W. Park, T. Schoepflin, Y. Kim. Active contour model with gradient directional information: Directional snake. IEEE Transactions on Circuits and Systems for Video Technology, vol. 11, no. 2, pp. 252–256, 2001. DOI:  https://doi.org/10.1109/76.905991.Google Scholar
  97. [97]
    J. S. Suri, K. C. Liu, S. Singh, S. N. Laxminarayan, X. L. Zeng, L. Reden. Shape recovery algorithms using levelsets in 2D/3D medical imagery: A state-of-the-art review. IEEE Transactions on Information Technology in Biomedicine, vol. 6, no. 1, pp. 8–28, 2002. DOI:  https://doi.org/10.1109/4233.992158.Google Scholar
  98. [98]
    W. J. Zhou, Z. X. Fei, H. S. Hu, L. Liu, J. N. Li, P. J. Smith. Real-time object subspace searching based on discrete searching paths and local energy. InternationalJournal of Automation and Computing, vol. 13, no. 2, pp. 99–107, 2016. DOI:  https://doi.org/10.1007/s11633-015-0946-2.Google Scholar
  99. [99]
    N. R. Pal, S. K. Pal. A review on image segmentation techniques. Pattern Recognition, vol. 26, no. 9, pp. 1277–1294, 1993. DOI:  https://doi.org/10.1016/0031-3203(93)90135-J.Google Scholar
  100. [100]
    H. D. Cheng, X. H. Jiang, Y. Sun, J. L. Wang. Color image segmentation: Advances and prospects. Pattern Recognition, vol. 34, no. 12, pp. 2259–2281, 2001. DOI:  https://doi.org/10.1016/S0031-3203(00)00149-7.zbMATHGoogle Scholar
  101. [101]
    R. C. Zhao, Y. D. Ma. A region segmentation method for region-oriented image compression. Neurocomputing, vol. 85, pp. 45–52, 2012. DOI:  https://doi.org/10.1016/j.neucom.2012.01.007.Google Scholar
  102. [102]
    P. Arbelaez. Boundary extraction in natural images using ultrametric contour maps. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, New York, USA, pp. 182–182, 2006. DOI:  https://doi.org/10.1109/CVPRW.2006.48.Google Scholar
  103. [103]
    P. Arbelaez, M. Maire, C. Fowlkes, J. Malik. From contours to regions: An empirical evaluation. In Proceedingsof IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Miami, USA, pp. 2294–2301, 2009. DOI:  https://doi.org/10.1109/CVPR.2009.5206707.Google Scholar
  104. [104]
    Y. S. Ming, H. D. Li, X. M. He. Winding number constrained contour detection. IEEE Transactions on ImageProcessing, vol. 24, no. 1, pp. 68–79, 2015. DOI:  https://doi.org/10.1109/TIP.2014.2372636.MathSciNetGoogle Scholar
  105. [105]
    Y. S. Ming, H. D. Li, X. M. He. Winding number for region-boundary consistent salient contour extraction. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Portland, USA, pp. 2818–2825, 2013. DOI:  https://doi.org/10.1109/CVPR.2013.363.Google Scholar
  106. [106]
    L. D. Cohen, E. Bardnient, N. Ayache. Surface reconstruction using active contour models. In Proceedings SPIE Conference on Geometric Methods in Computer Vision, San Diego, USA, 1993.Google Scholar
  107. [107]
    T. F. Chan, L. A. Vese. Active contours without edges. IEEE Transactions on Image Processing, vol. 10, no. 2, pp. 266–277, 2001. DOI:  https://doi.org/10.1109/83.902291.zbMATHGoogle Scholar
  108. [108]
    L. A. Vese, T. F. Chan. A multiphase level set framework for image segmentation using the Mumford and Shahmodel. International Journal of Computer Vision, vol. 53, no. 3, pp. 271–293, 2002. DOI:  https://doi.org/10.1023/A:1020874308076.zbMATHGoogle Scholar
  109. [109]
    A. Chakraborty, L. H. Staib, J. S. Duncan. Deformable boundary finding in medical images by integrating gradient and region information. IEEE Transactions on Medical Imaging, vol. 15, no. 6, pp. 859–870, 1996. DOI:  https://doi.org/10.1109/42.544503.Google Scholar
  110. [110]
    S. C. Zhu, A. Yuille. Region competition: Unifying snakes, region growing, and Bayes/MDL for multibandimage segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 9, pp. 884–900, 1996. DOI:  https://doi.org/10.1109/34.537343.Google Scholar
  111. [111]
    N. Paragios, R. Deriche. Geodesic active regions and level set methods for supervised texture segmentation. International Journal of Computer Vision, vol. 46, no. 3, pp. 223–247, 2002. DOI:  https://doi.org/10.1023/A:1014080923068.zbMATHGoogle Scholar
  112. [112]
    D. Cremers, F. Tischhuser, J. Weickert, C. Schnorr. Diffusion snakes: Introducing statistical shape knowledge into the Mumford-Shah functional. International Journal of Computer Vision, vol. 50, no. 3, pp. 295–313, 2002. DOI:  https://doi.org/10.1023/A:1020826424915.zbMATHGoogle Scholar
  113. [113]
    C. Collewet. Polar snakes: A fast and robust parametric active contour model. In Proceedings of the 16th IEEE International Conference on Image Processing, IEEE, Cairo, Egypt, pp. 3013–3016, 2009. DOI:  https://doi.org/10.1109/ICIP.2009.5414444.Google Scholar
  114. [114]
    B. Zhao, J. S. Feng, X. Wu, S. C. Yan. A survey on deep learning-based fine-grained object classification and semantic segmentation. International Journal of Automation and Computing, vol. 14, no. 2, pp. 119–135, 2017. DOI:  https://doi.org/10.1007/s11633-017-1053-3.Google Scholar
  115. [115]
    A. Krizhevsky, I. Sutskever, G. E. Hinton. ImageNet classification with deep convolutional neural networks. In Proceedings of Advances in Neural Information Processing Systems, Lake Tahoe, Spain, pp. 1097–1105, 2012. DOI:  https://doi.org/10.1145/3065386.Google Scholar
  116. [116]
    K. Simonyan, A. Zisserman. Very deep convolutional networks for large-scale image recognition. https://doi.org/arxiv.org/pdf/1409.1556.pdf
  117. [117]
    C. Szegedy, W. Liu, Y. Q. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich. Going deeper with convolutions. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston, USA, pp. 1–9, 2015. DOI:  https://doi.org/10.1109/CVPR.2015.7298594.Google Scholar
  118. [118]
    K. M. He, X. Y. Zhang, S. Q. Ren, J. Sun. Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, pp. 770–778, 2016. DOI:  https://doi.org/10.1109/CVPR.2016.90.Google Scholar
  119. [119]
    S. Ioffe, C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning, IEEE, Lille, France, pp. 448–456, 2015.Google Scholar
  120. [120]
    E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. https://doi.org/arxiv.org/pdf/1207.0580.pdf
  121. [121]
    Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, L. D. Jackel. Backpropagation applied to hand written zip code recognition. Neural Computation, vol. 1, no. 4, pp. 541–551, 1989. DOI:  https://doi.org/10.1162/neco.1989.1.4.541.Google Scholar
  122. [122]
    E. Shelhamer, J. Long, T. Darrell. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 4, pp. 640–651, 2017. DOI:  https://doi.org/10.1109/TPAMI.2016.2572683.Google Scholar
  123. [123]
    L. C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, A. L. Yuille. Semantic image segmentation with deep convolutional nets and fully connected CRFs. https://doi.org/arxiv.org/pdf/1412.7062.pdf
  124. [124]
    L. C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, A. L. Yuille. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fullyconnected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 4, pp. 834–848, 2018. DOI:  https://doi.org/10.1109/TPAMI.2017.2699184.Google Scholar
  125. [125]
    F. Yu, V. Koltun. Multi-scale context aggregation by dilated convolutions. https://doi.org/arxiv.org/pdf/1511.07122.pdf
  126. [126]
    H. Noh, S. Hong, B. Han. Learning deconvolution network for semantic segmentation. In Proceedings of IEEE International Conference on Computer Vision, IEEE,Santiago, Chile, pp. 1520–1528, 2015. DOI:  https://doi.org/10.1109/ICCV.2015.178.Google Scholar
  127. [127]
    V. Badrinarayanan, A. Kendall, R. Cipolla. SegNet: Adeep convolutional encoder-decoder architecture for image segmentation. https://doi.org/arxiv.org/pdf/1511.00561.pdf
  128. [128]
    P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, Y. LeCun. OverFeat: Integrated recognition, localizationand detection using convolutional networks. https://doi.org/arx-iv.org/pdf/1312.6229.pdf
  129. [129]
    J. F. Dai, K. M. He, J. Sun. BoxSup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In Proceedings of IEEE Conference onComputer Vision, IEEE, Santiago, Chile, pp. 1635–1643, 2015. DOI:  https://doi.org/10.1109/ICCV.2015.191.Google Scholar
  130. [130]
    P. O. Pinheiro, R. Collobert. Weakly supervised semantic segmentation with convolutional networks. https://doi.org/arxiv.org/pdf/1705.09052.pdf
  131. [131]
    S. Hong, H. Noh, B. Han. Decoupled deep neural networkfor semi-supervised semantic segmentation. In Proceedings of Advances in Neural Information Processing Systems, Montreal, Canada, pp. 1495–1503, 2015.Google Scholar
  132. [132]
    G. Papandreou, L. C. Chen, K. P. Murphy, A. L. Yuille. Weakly- and semi-supervised learning of a deep convolutional network for semantic image segmentation. In Proceedings of IEEE International Conference on Computer Vision, IEEE, Santiago, Chile, pp. 1742–1750, 2015. DOI:  https://doi.org/10.1109/ICCV.2015.203.Google Scholar
  133. [133]
    R. Girshick, J. Donahue, T. Darrell, J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of IEEE Conference onComputer Vision and Pattern Recognition, IEEE, Columbus, USA, pp. 580–587, 2014. DOI:  https://doi.org/10.1109/CV-PR.2014.81.Google Scholar
  134. [134]
    K. M. He, X. Y. Zhang, S. Q. Ren, J. Sun. Spatial pyramid pooling in deep convolutional networks for visual recognition. In Proceedings of the 13th European Conference on Computer Vision, Zurich, Switzerland, pp. 346–361, 2014. DOI:  https://doi.org/10.1007/978-3-319-10578-9_23.Google Scholar
  135. [135]
    S. Q. Ren, K. M. He, R. Girshick, J. Sun. Faster R-CNN:Towards real-time object detection with region proposal networks. In Proceedings of Advances in Neural Information Processing, Montreal, Canada, pp. 91–99, 2015.Google Scholar
  136. [136]
    Y. Ganin, V. Lempitsky. N.4-fields: Neural networknearest neighbor fields for image transforms. In Proceedings of the 12th Asian Conference on Computer Vision, Springer, Singapore, pp. 536–541, 2014. DOI:  https://doi.org/10.1007/978-3-319-16808-1_36.Google Scholar
  137. [137]
    W. Shen, X. G. Wang, Y. Wang, X. Bai, Z. J. Zhang. DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston, USA, pp. 3982–3991, 2015. DOI:  https://doi.org/10.1109/CVPR.2015.7299024.Google Scholar
  138. [138]
    J. J. Hwang, T. L. Liu. Pixel-wise deep learning for contour detection. https://doi.org/arxiv.org/pdf/1504.01989.pdf
  139. [139]
    G. Bertasius, J. B. Shi, L. Torresani. DeepEdge: A multi-scale bifurcated deep network for top-down contour detection. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston, USA, pp. 4380–4389, 2015. DOI:  https://doi.org/10.1109/CVPR.2015.7299067.Google Scholar
  140. [140]
    S. Xie, Z. W. Tu. Holistically-nested edge detection. In Proceedings of IEEE Conference on Computer Vision, IEEE, Santiago, Chile, pp. 1395–1403, 2015. DOI:  https://doi.org/10.1109/ICCV.2015.164.Google Scholar
  141. [141]
    Y. Liu, M. S. Lew. Learning relaxed deep supervision for better edge detection. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, pp. 231–240, 2016. DOI:  https://doi.org/10.1109/CVPR.2016.32.Google Scholar
  142. [142]
    Y. Liu, M. M. Cheng, X. W. Hu, K. Wang, X. Bai. Richer convolutional features for edge detection. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Honolulu, USA, 2017. DOI:  https://doi.org/10.1109/CVPR.2017.622.Google Scholar
  143. [143]
    K. K. Maninis, J. Pont-Tuset, P. Arbelaez, L. Van Gool. Convolutional oriented boundaries. In Proceedings of the 14th European Conference on Computer Vision, Springer, Amsterdam, The Netherlands, pp. 580–596, 2016. DOI:  https://doi.org/10.1007/978-3-319-46448-0_35.Google Scholar
  144. [144]
    C. Y. Lee, S. Xie, P. W. Gallagher, Z. Y. Zhang, Z. W. Tu. Deeply-supervised nets. In Proceedings of the 18 thInternational Conference on Artificial Intelligence andStatistics, JMLR, San Diego, USA, pp. 562–570, 2015.Google Scholar
  145. [145]
    J. R. R. Uijlings, V. Ferrari. Situational object boundary detection. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston,USA, pp. 4712–4721, 2015. DOI:  https://doi.org/10.1109/CVPR.2015.7299103.Google Scholar
  146. [146]
    A. Khoreva, R. Benenson, M. Omran, M. Hein, B. Schiele. Weakly supervised object boundaries. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, pp. 183–192, 2016. DOI:  https://doi.org/10.1109/CVPR.2016.27.Google Scholar
  147. [147]
    B. Hariharan, P. Arbelaez, L. Bourdev. Semantic contours from inverse detectors. In Proceedings of IEEE Conference on Computer Vision, IEEE, Barcelona, Spain, pp. 991–998, 2011. DOI:  https://doi.org/10.1109/CVPR.2016.27.Google Scholar

Copyright information

© Institute of Automation, Chinese Academy of Sciences and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Research Center of Precision Sensing and Control, Institute of AutomationChinese Academy of ScienceBeijingChina
  2. 2.University of Chinese Academy of ScienceBeijingChina
  3. 3.Tianjin Intelligent Technology Institute of Institute of AutomationChinese Academy of Science Co., LtdTianjinChina

Personalised recommendations