Advertisement

A novel contextual memory algorithm for edge detection

  • Alexandru DorobanţiuEmail author
  • Remus Brad
Short paper
  • 18 Downloads

Abstract

Edge detection plays an important role in many computer vision systems. In this paper, we propose a novel application agnostic algorithm for prediction of probabilities based on the contextual information available and then apply the algorithm for estimating the probability of pixels belonging to an edge using surrounding pixel values as local contexts. We then proceed to test different image transformations as input layers, such as the Canny edge detector. We propose two different architectures, one single layered and one multilayered, which approach the scaling problem by creating scaled side outputs and combining them via a logistic regression layer. We tested our approach on the BSDS500 edge detection dataset with optimistic results.

Keywords

Edge detection Local context Neural network Probabilistic method BSDS500 benchmark 

Notes

References

  1. 1.
    Gaonkar B, Hovda D, Martin N et al (2016) Deep learning in the small sample size setting: cascaded feed forward neural networks for medical image segmentation. Proc SPIE 9785:97852IGoogle Scholar
  2. 2.
    Milletari F, Navab N, Ahmadi S (2016) V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: IEEE fourth international conference on 3D vision, pp 565–571Google Scholar
  3. 3.
    Fram JR, Deutsch ES (1975) On the quantitative evaluation of edge detection schemes and their comparison with human performance. IEEE Trans Comput C-24:6:616–628CrossRefzbMATHGoogle Scholar
  4. 4.
    Arbelaez P, Maire M, Fowlkes C, Malik J (2011) Contour detection and hierarchical image segmentation. IEEE TPAMI 33(5):898–916CrossRefGoogle Scholar
  5. 5.
    Dollár P, Zitnick LC (2015) Fast edge detection using structured forests. IEEE Trans Pattern Anal Mach Intell 37(8):1558–1570CrossRefGoogle Scholar
  6. 6.
    Xie S, Tu Z (2017) Holistically-nested edge detection. Proc IEEE Int J Comput Vis 125(1):3–18MathSciNetCrossRefGoogle Scholar
  7. 7.
    Liu Y, Lew MS (2016) Learning relaxed deep supervision for better edge detection. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 231–240Google Scholar
  8. 8.
    Liu Y, Cheng MM et al (2019) Richer convolutional features for edge detection. In: IEEE transactions on pattern analysis and machine intelligence; http://mftp.mmcheng.net/Papers/19PamiEdge.pdf. Accessed 05 Nov 2018
  9. 9.
    Fu F, Wang C et al (2018) An improved adaptive edge detection algorithm based on Canny. In: Proceedings of SPIE 10827 icOPEN. Accessed 24 Jul 2018Google Scholar
  10. 10.
    Guadaa C, Edwin Zarrazolab et al (2018) A novel edge detection algorithm based on a hierarchical graph-partition approach. J Intell Fuzzy Syst 34:1875–1892CrossRefGoogle Scholar
  11. 11.
    Minka T (2017) A comparison of numerical optimizers for logistic regression. https://tminka.github.io/papers/logreg/minka-logreg.pdf. Accessed 05 Feb 2017
  12. 12.
    Naftaly U, Intrator N, Horn D (1999) Optimal ensemble averaging of neural networks. Netw Comput Neural Syst 8:3zbMATHGoogle Scholar
  13. 13.
    Liu Y, Yao X (1999) Ensemble learning via negative correlation. Neural Netw 12(10):1399–1404CrossRefGoogle Scholar
  14. 14.
    Long PM, Servedio RA (2010) Random classification noise defeats all convex potential boosters. Mach Learn 78(3):287–304MathSciNetCrossRefGoogle Scholar
  15. 15.
  16. 16.
  17. 17.
    Mattern C (2012) Mixing strategies in data compression. In: Proceedings of the 22nd data compression conference (DCC), pp 337–346Google Scholar
  18. 18.
    Mahoney M (2005) Adaptive weighing of context models for lossless data compression. http://mattmahoney.net/dc/cs200516.pdf. Accessed 05 Feb 2017
  19. 19.
  20. 20.
    Wang Y, Zhao X et al (2018) Deep crisp boundaries. From boundaries to higher-level tasks. arXiv preprint arXiv:1801.02439
  21. 21.
    Xu D, Ouyang W et al (2017) Learning deep structured multi-scale features using attention-gated CRFs for contour prediction. In: Advances in neural information processing system, pp 3961–3970Google Scholar
  22. 22.
    Yu Z, Feng C et al (2017) CASENet: deep category-aware semantic edge detection. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 21–26Google Scholar
  23. 23.
    Yang J, Price B et al (2016) Object contour detection with a fully convolutional encoder-decoder network. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 193–202Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Computer Science DepartmentLucian Blaga University of SibiuSibiuRomania

Personalised recommendations