Skip to main content

Advertisement

Springer Nature Link
Log in

Learning Grayscale Mathematical Morphology with Smooth Morphological Layers

  • Published:
Journal of Mathematical Imaging and Vision Aims and scope Submit manuscript

Abstract

The integration of mathematical morphology operations within convolutional neural network architectures has received an increasing attention lately. However, replacing standard convolution layers by morphological layers performing erosions or dilations is particularly challenging because the \(\min \) and \(\max \) operations are not differentiable. P-convolution layers were proposed as a possible solution to this issue since they can act as smooth differentiable approximation of \(\min \) and \(\max \) operations, yielding pseudo-dilation or pseudo-erosion layers. In a recent work, we proposed two novel morphological layers based on the same principle as the p-convolution, while circumventing its principal drawbacks, and showcased their capacity to efficiently learn grayscale morphological operators while raising several edge cases. In this work, we complete those previous results by thoroughly analyzing the behavior of the proposed layers and by investigating and settling the reported edge cases. We also demonstrate the compatibility of one of the proposed morphological layers with binary morphological frameworks.

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
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

References

  1. Angulo, J.: Pseudo-morphological image diffusion using the counter-harmonic paradigm. In: International Conference on Advanced Concepts for Intelligent Vision Systems. Springer, pp. 426–437 (2010)

  2. Bloch, I., Blusseau, S., Pérez, R.P., Puybareau, É., Tochon, G.: On some associations between mathematical morphology and artificial intelligence. In: International Conference on Discrete Geometry and Mathematical Morphology. Springer, pp. 457–469 (2021)

  3. Bullen, P.S.: Handbook of Means and Their Inequalities, vol. 560. Springer, Berlin (2013)

    MATH  Google Scholar 

  4. Calafiore, G.C., Gaubert, S., Possieri, C.: Log-sum-exp neural networks and posynomial models for convex and log-log-convex data. IEEE Trans. Neural Netw. Learn. Syst. 31(3), 827–838 (2019)

    Article  MathSciNet  Google Scholar 

  5. Charisopoulos, V., Maragos, P.: Morphological perceptrons: geometry and training algorithms. In: International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing. Springer, pp. 3–15 (2017)

  6. Dalla Mura, M., Benediktsson, J.A., Bruzzone, L.: Alternating sequential filters with morphological attribute operators for the analysis of remote sensing images. In: Image and Signal Processing for Remote Sensing XVI, vol. 7830. International Society for Optics and Photonics, p. 783006 (2010)

  7. Davidson, J.L., Ritter, G.X.: Theory of morphological neural networks. In: Digital Optical Computing II, vol. 1215. International Society for Optics and Photonics, pp. 378–388 (1990)

  8. Franchi, G., Fehri, A., Yao, A.: Deep morphological networks. Pattern Recogn. 102, 107246 (2020)

    Article  Google Scholar 

  9. Hassoun, M.H., et al.: Fundamentals of Artificial Neural Networks. MIT Press, Cambridge (1995)

    MATH  Google Scholar 

  10. Hernández, G., Zamora, E., Sossa, H., Téllez, G., Furlán, F.: Hybrid neural networks for big data classification. Neurocomputing 390, 327–340 (2020)

    Article  Google Scholar 

  11. Kirszenberg, A., Tochon, G., Puybareau, É., Angulo, J.: Going beyond p-convolutions to learn grayscale morphological operators. In: International Conference on Discrete Geometry and Mathematical Morphology. Springer, pp. 470–482 (2021)

  12. Lange, M., Zühlke, D., Holz, O., Villmann, T., Mittweida, S.G.: Applications of Lp-norms and their smooth approximations for gradient based learning vector quantization. In: ESANN, pp. 271–276 (2014)

  13. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)

    Article  Google Scholar 

  14. LeCun, Y., Cortes, C., Burges, C.J.: The MNIST database of handwritten digits, 10(34), 14. http://yann.lecun.com/exdb/mnist (1998)

  15. Masci, J., Angulo, J., Schmidhuber, J.: A learning framework for morphological operators using counter–harmonic mean. In: International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing. Springer, pp. 329–340 (2013)

  16. Mellouli, D., Hamdani, T.M., Ayed, M.B., Alimi, A.M.: Morph-cnn: a morphological convolutional neural network for image classification. In: International Conference on Neural Information Processing. Springer, pp. 110–117 (2017)

  17. Mellouli, D., Hamdani, T.M., Sanchez-Medina, J.J., Ayed, M.B., Alimi, A.M.: Morphological convolutional neural network architecture for digit recognition. IEEE Trans. Neural Netw. Learn. Syst. 30(9), 2876–2885 (2019)

    Article  Google Scholar 

  18. Mondal, R., Dey, M.S., Chanda, B.: Image restoration by learning morphological opening–closing network. Math. Morphol. Theory Appl. 4(1), 87–107 (2020)

    MATH  Google Scholar 

  19. Nogueira, K., Chanussot, J., Dalla Mura, M., Schwartz, W.R., Santos, J.A.d.: An introduction to deep morphological networks. arXiv preprint arXiv:1906.01751 (2019)

  20. Pessoa, L.F., Maragos, P.: Neural networks with hybrid morphological/rank/linear nodes: a unifying framework with applications to handwritten character recognition. Pattern Recogn. 33(6), 945–960 (2000)

    Article  Google Scholar 

  21. Ritter, G.X., Sussner, P.: An introduction to morphological neural networks. In: Proceedings of 13th International Conference on Pattern Recognition, vol. 4. IEEE, pp. 709–717 (1996)

  22. Roy, S.K., Mondal, R., Paoletti, M.E., Haut, J.M., Plaza, A.J.: Morphological convolutional neural networks for hyperspectral image classification. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. (2021)

  23. Serra, J.: Image Analysis and Mathematical Morphology. Academic Press, New York (1983)

    Google Scholar 

  24. Serra, J., Vincent, L.: An overview of morphological filtering. Circuits Syst. Signal Process. 11(1), 47–108 (1992)

    Article  MathSciNet  Google Scholar 

  25. Shen, Y., Zhong, X., Shih, F.Y.: Deep morphological neural networks. arXiv preprint arXiv:1909.01532 (2019)

  26. Shih, F.Y., Shen, Y., Zhong, X.: Development of deep learning framework for mathematical morphology. Int. J. Pattern Recogn. Artif Intell. 33(06), 1954024 (2019)

    Article  Google Scholar 

  27. Soille, P.: Morphological Image Analysis: Principles and Applications. Springer, Berlin (2013)

    MATH  Google Scholar 

  28. Sussner, P.: Morphological perceptron learning. In: Proceedings of the 1998 IEEE International Symposium on Intelligent Control (ISIC). IEEE, pp. 477–482 (1998)

  29. Sussner, P., Campiotti, I.: Extreme learning machine for a new hybrid morphological/linear perceptron. Neural Netw. 123, 288–298 (2020)

    Article  Google Scholar 

  30. Sussner, P., Esmi, E.L.: Morphological perceptrons with competitive learning: lattice-theoretical framework and constructive learning algorithm. Inf. Sci. 181(10), 1929–1950 (2011)

    Article  MathSciNet  Google Scholar 

  31. Valle, M.E.: Reduced dilation-erosion perceptron for binary classification. Mathematics 8(4), 512 (2020)

  32. Wilson, S.S.: Morphological networks. In: Visual Communications and Image Processing IV, vol. 1199. International Society for Optics and Photonics, pp. 483–495 (1989)

  33. Zamora, E., Sossa, H.: Dendrite morphological neurons trained by stochastic gradient descent. Neurocomputing 260, 420–431 (2017)

    Article  Google Scholar 

  34. Zhang, Y., Blusseau, S., Velasco-Forero, S., Bloch, I., Angulo, J.: Max-plus operators applied to filter selection and model pruning in neural networks. In: International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing. Springer, pp. 310–322 (2019)

Download references

Author information

Authors and Affiliations

  1. EPITA Research and Development Laboratory (LRDE), Le Kremlin-Bicêtre, France

    Romain Hermary, Guillaume Tochon, Élodie Puybareau & Alexandre Kirszenberg

  2. Centre for Mathematical Morphology, Mines ParisTech, PSL Research University, Fontainebleau, France

    Jesús Angulo

Authors
  1. Romain Hermary
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Guillaume Tochon
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Élodie Puybareau
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Alexandre Kirszenberg
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Jesús Angulo
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Guillaume Tochon.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hermary, R., Tochon, G., Puybareau, É. et al. Learning Grayscale Mathematical Morphology with Smooth Morphological Layers. J Math Imaging Vis 64, 736–753 (2022). https://doi.org/10.1007/s10851-022-01091-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10851-022-01091-1

Keywords