Skip to main content
Springer Nature Link
Log in

A low-complexity residual deep neural network for image edge detection

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

In many computer vision and image processing applications, edge detection is a crucial step. However, in real time applications both the accuracy and the time complexity of edge detection are very important. Even though the performance of image edge detection techniques can be greatly improved through the use of deep convolutional neural networks (DCNNs), such networks generally result in a significantly increased computational complexity. Several techniques have been developed for edge detection based on the VGG16 network, since the convolutional layers of the networks of such schemes have fewer parameters than those of the existing residual networks such as ResNet50. However, their performance is inferior to that of the residual techniques and their computational complexity is still very large. In this article, a DCNN based on the VGG-16 architecture, with a focus on a significantly reduced complexity but with a performance that is comparable or superior to those of all the other existing edge detection techniques, is proposed. The objective of significantly reduced complexity of the network is achieved through the use of fire modules so much so that it is possible to increase the depth of the network while keeping its character of low complexity. This along with the use of residual learning allows to maintain or even to improve the performance of the network. The objectives of the proposed scheme are validated by conducting experiments employing two different datasets.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability

The datasets used in this paper are publicly available on the internet.

References

  1. Liao B, Hu J, Gilmore RO (2021) Optical flow estimation combining with illumination adjustment and edge refinement in livestock uav videos. Comput Electron Agric 180:105910

    Article  Google Scholar 

  2. Huang Z, Yang S, Zhou MC, Li Z, Gong Z, Chen Y (2022) Feature map distillation of thin nets for low-resolution object recognition. IEEE Trans Image Process

  3. Bansal M, Kumar M (2021) Kumar, m.: 2d object recognition techniques: state-of-the-art work. Arch Computat Methods Eng 28(3):1147–1161

    Article  Google Scholar 

  4. Yang Y, Zhao X, Huang M, Wang X, Zhu Q (2021) Multispectral image based germination detection of potato by using supervised multiple threshold segmentation model and canny edge detector. Comput Electron Agric 1827:106041

    Article  Google Scholar 

  5. Gandhi M, Kamdar J, Shah M (2020) Preprocessing of non-symmetrical images for edge detection. Augmented Human Res 5(1):1–10

    Article  Google Scholar 

  6. Gao F, Li Y, Lu S (2021) Extracting moving objects more accurately: a cda contour optimizer. IEEE Trans Circuits Syst Video Technol

  7. Manno-Kovacs A (2018) Direction selective contour detection for salient objects. IEEE Trans Circuits Syst Video Technol 29(2):375–389

    Article  Google Scholar 

  8. Tu Z, Ma Y, Li C, Tang J, Luo B (2020) Edge-guided non-local fully convolutional network for salient object detection. IEEE Trans Circuits Syst Video Technol 31(2):582–593

    Article  Google Scholar 

  9. Wu R, Feng M, Guan W, Wang D, Lu H, Ding E (2019) A mutual learning method for salient object detection with intertwined multi-supervision. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 8150– 8159

  10. Zeelan Basha C, Sai Teja T, Ravi Teja T, Harshita C, Rohith Sri Sai M (2021) Advancement in classification of x-ray images using radial basis function with support of canny edge detection model. In: Computational vision and bio-inspired computing, pp 29–40

  11. Dhruv B, Mittal N, Modi M (2021) Early and precise detection of pancreatic tumor by hybrid approach with edge detection and artificial intelligence techniques. EAI Endorsed Trans Pervasive Health Technol:1

  12. Al-Amaren A, Ahmad MO, Swamy MNS (2021) A very fast edge map-based algorithm for accurate motion estimation. SIViP:1–8

  13. Sobel I, Feldman G (1968) A 3x3 isotropic gradient operator for image processing. In: Presented at the stanford artificial intelligence project

  14. Prewitt JM (1970) Object enhancement and extraction. Picture Processing and Psychopictorics 10(1):15–19

    Google Scholar 

  15. Roberts L (1965) Machine perception of 3-D solids-series. Optical and electro-optical information processing. MIT Press

  16. Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal

  17. Scharcanski J, Venetsanopoulos AN (1997) Edge detection of color images using directional operators. IEEE Trans Circuits Syst Video Technol 7(2):397–401

    Article  Google Scholar 

  18. Haralick RM (1987) Digital step edges from zero crossing of second directional derivatives. In: Readings in computer vision, pp 216–226

  19. Huertas A, Medioni G (1986) Detection of intensity changes with subpixel accuracy using laplacian-gaussian masks. IEEE Trans Pattern Anal Mach Intell, (5), pp 651–664

  20. Nie Y, Cao X, Li P, Zhang Q, Zhang Z, Li G, Sun H (2019) Interactive contour extraction via sketch-alike dense-validation optimization. IEEE Trans Circuits Syst Video Technol 30(4):903–916

    Article  Google Scholar 

  21. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105

  22. Ganin Y, Lempitsky V (2014) N4-fields: neural network nearest neighbor fields for image transforms. In: Asian conference on computer vision. Springer, pp 536–551

  23. Bertasius G, Shi J, Torresani L (2015) Deepedge: a multi-scale bifurcated deep network for top-down contour detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4380–4389

  24. Shen W, Wang X, Wang Y, Bai X, Zhang Z (2015) Deepcontour: a deep convolutional feature learned by positive-sharing loss for contour detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3982– 3991

  25. Hwang J-J, Liu T-L (2015) Pixel-wise deep learning for contour detection. arXiv:1504.01989

  26. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556

  27. Xie S, Tu Z (2015) Holistically-nested edge detection. In: Proceedings of The IEEE international conference on computer vision, pp 1395–1403

  28. Liu Y, Lew MS (2016) Learning relaxed deep supervision for better edge detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 231–240

  29. Wang Y, Zhao X, Li Y, Huang K (2018) Deep crisp boundaries: from boundaries to higher-level tasks. IEEE Trans Image Process 28(3):1285–1298

    Article  MathSciNet  MATH  Google Scholar 

  30. Liu Y, Cheng M-M, Hu X, Bian J-W, Zhang L, Bai X, Tang J (2019) Richer convolutional features for edge detection. IEEE Trans Pattern Anal Mach Intell 41(8):1939–1946

    Article  Google Scholar 

  31. He J, Zhang S, Yang M, Shan Y, Huang T (2020) Bdcn: bi-directional cascade network for perceptual edge detection. IEEE Trans Pattern Anal Mach Intell

  32. Lin C, Zhang Z, Hu Y (2022) Bio-inspired feature enhancement network for edge detection. Appl Intell:1–16

  33. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  34. Poma XS, Riba E, Sappa A (2020) Dense extreme inception network: towards a robust cnn model for edge detection. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 1923–1932

  35. Hu Y, Belkhir N, Angulo J, Yao A, Franchi G (2021) Learning deep morphological networks with neural architecture search. arXiv:2106.07714

  36. Su Z, Liu W, Yu Z, Hu D, Liao Q, Tian Q, Pietikäinen M, Liu L (2021) Pixel difference networks for efficient edge detection. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 5117–5127

  37. Al-Amaren A, Ahmad MO, Swamy MNS (2021) RHN: a residual holistic neural network for edge detection. IEEE Access 9:74646–74658

    Article  Google Scholar 

  38. Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) Squeezenet: alexnet-level accuracy with 50x fewer parameters and < 0.5 mb model size. arXiv:1602.07360

  39. Qassim H, Verma A, Feinzimer D (2018) Compressed residual-vgg16 cnn model for big data places image recognition. In: 2018 IEEE 8th annual computing and communication workshop and conference (CCWC). IEEE, pp 169–175

  40. Peng C, Zhang X, Yu G, Luo G, Sun J (2017) Large kernel matters–improve semantic segmentation by global convolutional network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4353–4361

  41. Isola P, Zoran D, Krishnan D, Adelson EH (2014) Crisp boundary detection using pointwise mutual information. In: European conference on computer vision. Springer, pp 799–814

  42. Arbelaez P, Maire M, Fowlkes C, Malik J (2010) Contour detection and hierarchical image segmentation. IEEE Trans Pattern Anal Mach Intell 33(5):898–916

    Article  Google Scholar 

  43. Martin DR, Fowlkes CC, Malik J (2004) Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans Pattern Anal Mach Intell 26(5):530– 549

    Article  Google Scholar 

  44. Isola P, Zoran D, Krishnan D, Adelson EH (2014) Crisp boundary detection using pointwise mutual information. In: European conference on computer vision. Springer, pp 799–814

  45. Silberman N, Hoiem D, Kohli P, Fergus R (2012) Indoor segmentation and support inference from rgbd images. In: European conference on computer vision. Springer, pp 746– 760

  46. Mottaghi R, Chen X, Liu X, Cho N-G, Lee S-W, Fidler S, Urtasun R, Yuille A (2014) The role of context for object detection and semantic segmentation in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 891–898

  47. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980

  48. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning. PMLR, pp 448–456

  49. Jaron C (2017) Glossary of deep learning: batch normalisation, Accessed 16 June 2022. [Online]. Available: https://medium.com/deeper-learning/glossary-of-deep-learning-batch-normalisation-8266dcd2fa82

  50. Shashank R (2017) A guide to an efficient way to build neural network architectures- Part II: hyper-parameter selection and tuning for convolutional neural networks using hyperas on fashion-MNIST, Accessed 16 June 2022. [Online]. Available: https://towardsdatascience.com/a-guide-to-an-efficient-way-to-build-neural-network-architectures-part-ii-hyper-parameter-42efca01e5d7

  51. Chollet F et al (2015) GitHub, Accessed 13 Jan 2022. [Online]. Available: https://keras.io

  52. Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M et al (2019) Tensorflow: large-scale machine learning on heterogeneous systems. 2015. software available from tensorflow. org. https://www.tensorflow.org. Accessed 19 Aug 2022

  53. Dollár P, Zitnick CL (2014) Fast edge detection using structured forests. IEEE Trans Pattern Anal Mach Intell 37(8):1558–1570

    Article  Google Scholar 

  54. Pu M, Huang Y, Guan Q, Ling H (2021) Rindnet: Edge detection for discontinuity in reflectance, illumination, normal and depth. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 6879–6888

Download references

Acknowledgements

This work was supported in part by the Natural Sciences and Engineering Research Council of Canada, and in part by the Regroupment Strategique en Microelectronique du Quebec.

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, Concordia University, Montreal, H3G 1M8, QC, Canada

    Abdullah Al-Amaren, M. Omair Ahmad & M.N.S. Swamy

Authors
  1. Abdullah Al-Amaren
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. M. Omair Ahmad
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. M.N.S. Swamy
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to M. Omair Ahmad.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Al-Amaren, A., Ahmad, M.O. & Swamy, M. A low-complexity residual deep neural network for image edge detection. Appl Intell 53, 11282–11299 (2023). https://doi.org/10.1007/s10489-022-04062-6

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-04062-6

Keywords