Skip to main content

Image Contours Detection with Deep Features and SVM

  • Conference paper
  • First Online:
Advances in Fuzzy Logic and Technology 2017 (EUSFLAT 2017, IWIFSGN 2017)

Abstract

This contribution introduces the image contours detection based on the features extracted by a deep convolutional neural network. Popular pre-trained network VGG19 was used to extract 5504 different features for each input image pixel and then classified by a neural network with SVM classifier.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    The labels contain information whenever a pixel is or is not an edge.

  2. 2.

    The output of the convolutional layer.

  3. 3.

    The softmax outputs probabilities for pixel being edge and non edge pixel in one-hot codding, i.e. (1.0, 0.0) for pixel being edge pixel and (0.0, 1.0) for not being edge pixel.

References

  1. Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)

    Article  Google Scholar 

  2. Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 6, 679–698 (1986)

    Article  Google Scholar 

  3. Chang, M.: Applied deep learning 11/03 convolutional neural networks. https://www.slideshare.net/ckmarkohchang/applied-deep-learning-1103-convolutional-neural-networks. Accessed 27 May 2017

  4. Hwang, J.-J., Liu, T.-L.: Contour detection using cost-sensitive convolutional neural networks. CoRR, abs/1412.6857 (2014)

    Google Scholar 

  5. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates, Inc. (2012)

    Google Scholar 

  6. Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.S., Berg, A.C., Li, F.-F.: Imagenet large scale visual recognition challenge. CoRR, abs/1409.0575 (2014)

    Google Scholar 

  7. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556 (2014)

    Google Scholar 

  8. Ziou, D., Tabbone, S., et al.: Edge detection techniques-an overview. Pattern Recogn. Image Anal. C/C Raspoznavaniye Obrazov I Analiz Izobrazhenii 8, 537–559 (1998)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Vojtech Molek .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer International Publishing AG

About this paper

Cite this paper

Molek, V. (2018). Image Contours Detection with Deep Features and SVM. In: Kacprzyk, J., Szmidt, E., Zadrożny, S., Atanassov, K., Krawczak, M. (eds) Advances in Fuzzy Logic and Technology 2017. EUSFLAT IWIFSGN 2017 2017. Advances in Intelligent Systems and Computing, vol 642. Springer, Cham. https://doi.org/10.1007/978-3-319-66824-6_48

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-66824-6_48

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-66823-9

  • Online ISBN: 978-3-319-66824-6

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics