access icon free Active Canny: edge detection and recovery with open active contour models

© The Institution of Engineering and Technology
Received 04/04/2017, Accepted 12/09/2017, Revised 31/07/2017, Published 22/09/2017

The authors introduce an edge detection and recovery framework based on open active contour models (snakelets) to mitigate the problem of noisy or broken edges produced by classical edge detection algorithms, like Canny. The idea is to utilise the local continuity and smoothness cues provided by strong edges and grow them to recover the missing edges. This way, the strong edges are used to recover weak or missing edges by considering the local edge structures, instead of blindly linking edge pixels based on a threshold. The authors initialise short snakelets on the gradient magnitudes or binary edges automatically and then deform and grow them under the influence of gradient vector flow. The output snakelets are able to recover most of the breaks or weak edges and provide a smooth edge representation of the image; they can also be used for higher-level analysis, like contour segmentation.

Inspec keywords: image representation; edge detection; image restoration

Other keywords: high-level analysis; gradient magnitudes; output snakelets; open active contour model; local edge structures; active canny; recovery framework; local continuity; edge detection; binary edges; contour segmentation; missing edge recovery; gradient vector flow; image edge representation; smoothness cues; edge pixels

Subjects: Image recognition; Computer vision and image processing techniques

References

    1. 1)
      • 10. Hwang, J.J., Liu, T.L.: ‘Pixel-wise deep learning for contour detection’, arXiv preprint arXiv:150401989, 2015.
    2. 2)
      • 6. Shen, W., Wang, X., Wang, Y., et al: ‘Deepcontour: a deep convolutional feature learned by positive-Sharing loss for contour detection’. IEEE Conf. Computer Vision and Pattern Recognition, 2015, Boston, Massachusetts, USA, pp. 3982–3991.
    3. 3)
      • 26. Bukhari, S.S., Shafait, F., Breuel, T.: ‘Segmentation of curled textlines using active contours’. IAPR Workshop on Document Analysis Systems, 2008, Nara, Japan, pp. 270–277.
    4. 4)
      • 27. Bukhari, S.S., Shafait, F., Breuel, T.: ‘Coupled snakelets for curled text-line segmentation from warped document images’, Int. J. Doc. Anal. Rec., 2013, 16, (1), pp. 33–53.
    5. 5)
      • 15. Arbelaez, P., Maire, M., Fowlkes, C., et al: ‘Contour detection and hierarchical image segmentation’, IEEE Trans. Pattern Anal., 2011, 33, (5), pp. 898–916.
    6. 6)
      • 4. Xu, C., Prince, J.L.: ‘Snakes, shapes, and gradient vector flow’, IEEE Trans. Image Process, 1998, 7, (3), pp. 359–369.
    7. 7)
      • 5. Martin, D.R., Fowlkes, C.C., Malik, J.: ‘Learning to detect natural image boundaries using local brightness, color, and texture cues’, IEEE Trans. Pattern Anal., 2004, 26, (5), pp. 530–549.
    8. 8)
      • 7. Szeliski, R.: ‘Computer vision: algorithms and Applications’ (Springer-Verlag, London, 2010).
    9. 9)
      • 24. Wang, Y., Narayanaswamy, A., Tsai, C.L., et al: ‘A broadly applicable 3-D neuron tracing method based on open-curve snake’, Neuroinformatics, 2011, 9, (2–3), pp. 193–217.
    10. 10)
      • 16. Dollár, P., Zitnick, C.L.: ‘Fast edge detection using structured forests’, IEEE Trans. Pattern Anal., 2015, 37, (8), pp. 1558–1570.
    11. 11)
      • 3. Papari, G., Petkov, N.: ‘Edge and line oriented contour detection: state of the Art’, Image Vis. Comput., 2011, 29, (2), pp. 79–103.
    12. 12)
      • 14. Liu, Y., Lew, M.S.: ‘Learning relaxed deep supervision for better edge detection’. IEEE Conf. Computer Vision and Pattern Recognition, Las Vegas, USA, 2016.
    13. 13)
      • 9. Bertasius, G., Shi, J., Torresani, L.: ‘DeepEdge: a multi-Scale bifurcated deep network for top-Down contour detection’. IEEE Conf. Computer Vision and Pattern Recognition, 2015.
    14. 14)
      • 12. Xie, S., Tu, Z.: ‘Holistically-nested edge detection’, Int. J. Comput. Vis., 2017, pp. 1–16.
    15. 15)
      • 17. Ren, X., Fowlkes, C.C., Malik, J.: ‘Scale-Invariant contour completion using conditional random fields’. IEEE Int. Conf. Computer Vision. 2005, Beijing, China, pp. 1214–1221.
    16. 16)
      • 11. Li, Y., Paluri, M., Rehg, J.M., et al: ‘Unsupervised learning of edges’. IEEE Conf. Computer Vision and Pattern Recognition, Las Vegas, USA, 2016.
    17. 17)
      • 19. Ming, Y., Li, H., He, X.: ‘Connected contours: a New contour completion model that respects the closure effect’. IEEE Conf. Computer Vision and Pattern Recognition, 2012, Providence, Rhode Island, USA, pp. 829–836.
    18. 18)
      • 28. Smith, M.B., Li, H., Shen, T., et al: ‘Segmentation and tracking of cytoskeletal filaments using open active contours’, Cytoskeleton, 2010, 67, (11), pp. 693–705.
    19. 19)
      • 25. Wang, Y., Narayanaswamy, A., Roysam, B.: ‘Novel 4-D open-curve active contour and curve completion approach for automated tree structure extraction’. Computer Vision and Pattern Recognition, Colorado Springs, USA, 2011, pp. 1105–1112.
    20. 20)
      • 23. Xu, T., Li, H., Shen, T., et al: ‘Extraction and analysis of actin networks based on open active contour models’. IEEE Int. Symp. Biomedical Imaging, Piscataway, NJ, USA, 2011, pp. 1334–1340.
    21. 21)
      • 8. Hallman, S., Fowlkes, C.C.: ‘Oriented edge forests for boundary detection’. IEEE Conf. Computer Vision and Pattern Recognition, Boston, Massachusetts, USA, 2015.
    22. 22)
      • 1. Van De Weijer, J., Gevers, T., Smeulders, A.W.M.: ‘Robust photometric invariant features from the color tensor’, IEEE Trans. Image Process., 2006, 15, (1), pp. 118–127.
    23. 23)
      • 21. Li, H., Shen, T., Vavylonis, D., et al: ‘Actin filament tracking based on particle filters and stretching open active contour models’. Int. Conf. Medical Image Computing and Computer Assisted Intervention, London, UK, 2009, pp. 673–681.
    24. 24)
      • 18. Ren, X., Fowlkes, C.C., Malik, J.: ‘Learning probabilistic models for contour completion in natural images’, Int. J. Comput. Vis., 2008, 77, (1–3), pp. 47–63.
    25. 25)
      • 20. Kass, M., Witkin, A., Terzopoulos, D.: ‘Snakes: active contour models’, Int. J. Comput. Vis., 1988, 1, (4), pp. 1162–1173.
    26. 26)
      • 2. Canny, J.: ‘A computational approach to edge detection’, IEEE Trans. Pattern Anal., 1986, 8, (6), pp. 679–698.
    27. 27)
      • 22. Li, H., Shen, T., Smith, M.B., et al: ‘Automated actin filament segmentation, tracking and tip elongation measurements based on open active contour models’. IEEE Int. Symp. on Biomedical Imaging, 2009, pp. 1302–1305.
    28. 28)
      • 13. Liu, Y., Cheng, M.M., Hu, X., et al: ‘Richer convolutional features for edge detection’. IEEE Conf. Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, 2017.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2017.0336
Loading

Related content

content/journals/10.1049/iet-ipr.2017.0336
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading