Skip to main content
Springer Nature Link
Log in

Logarithmic Morphological Neural Nets Robust to Lighting Variations

  • Conference paper
  • First Online:
Discrete Geometry and Mathematical Morphology (DGMM 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13493))

Abstract

Morphological neural networks allow to learn the weights of a structuring function knowing the desired output image. However, those networks are not intrinsically robust to lighting variations in images with an optical cause, such as a change of light intensity. In this paper, we introduce a morphological neural network which possesses such a robustness to lighting variations. It is based on the recent framework of Logarithmic Mathematical Morphology (LMM), i.e. Mathematical Morphology defined with the Logarithmic Image Processing (LIP) model. This model has a LIP additive law which simulates in images a variation of the light intensity. We especially learn the structuring function of a LMM operator robust to those variations, namely: the map of LIP-additive Asplund distances. Results in images show that our neural network verifies the required property.

Supported by Lyon Informatics Federation, France, through the “FakeNets” project.

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

Access this chapter

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

Chapter
USD 29.95
Price excludes VAT (USA)
eBook
USD 39.99
Price excludes VAT (USA)
Softcover Book
USD 54.99
Price excludes VAT (USA)

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Aouad, T., Talbot, H.: Binary morphological neural network (2022). https://doi.org/10.48550/ARXIV.2203.12337

    Article  Google Scholar 

  2. Barrera, J., Dougherty, E.R., Tomita, N.S.: Automatic programming of binary morphological machines by design of statistically optimal operators in the context of computational learning theory. Journal of Electronic Imaging 6(1), 54–67 (1997). https://doi.org/10.1117/12.260010

    Article  Google Scholar 

  3. Brailean, J., Sullivan, B., Chen, C., Giger, M.: Evaluating the EM algorithm for image processing using a human visual fidelity criterion. In: ICASSP 1991. pp. 2957–2960 vol 4 (1991). https://doi.org/10.1109/ICASSP.1991.151023

  4. Chaman, A., Dokmanić, I.: Truly shift-invariant convolutional neural networks. In: CVPR 2021. pp. 3772–3782 (2021). https://doi.org/10.1109/CVPR46437.2021.00377

  5. Charisopoulos, V., Maragos, P.: Morphological perceptrons: Geometry and training algorithms. In: Lect Notes Comput Sc. vol. 10225, pp. 3–15. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-57240-6_1

  6. Davidson, J.L., Hummer, F.: Morphology neural networks: An introduction with applications. Circuits, Systems and Signal Processing 12(2), 177–210 (1993). https://doi.org/10.1007/BF01189873

  7. Franchi, G., Fehri, A., Yao, A.: Deep morphological networks. Pattern Recognition 102, 107246 (2020). https://doi.org/10.1016/j.patcog.2020.107246

    Article  Google Scholar 

  8. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016), https://www.deeplearningbook.org

  9. Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer, New York, NY, 2 edn. (2009). https://doi.org/10.1007/978-0-387-84858-7

  10. Heijmans, H., Ronse, C.: The algebraic basis of mathematical morphology I. Dilations and erosions. Comput. Vision Graphics and Image Process. 50(3), 245–295 (Jun 1990). https://doi.org/10.1016/0734-189X(90)90148-O

  11. Jourlin, M.: Chapter three - metrics based on logarithmic laws. In: Logarithmic Image Processing: Theory and Applications, Adv. Imag. Electron Phys., vol. 195, pp. 61–113. Elsevier (2016). https://doi.org/10.1016/bs.aiep.2016.04.003

  12. Jourlin, M., Pinoli, J.: Logarithmic image processing: The mathematical and physical framework for the representation and processing of transmitted images. Adv. Imag. Electron Phys., vol. 115, pp. 129–196. Elsevier (2001). https://doi.org/10.1016/S1076-5670(01)80095-1

  13. Jourlin, M.: Logarithmic Image Processing: Theory and Applications, Adv. Imag. Electron Phys., vol. 195. Elsevier (2016)

    Google Scholar 

  14. Jourlin, M., Pinoli, J.C.: Image dynamic range enhancement and stabilization in the context of the logarithmic image processing model. Signal Process. 41(2), 225–237 (1995). https://doi.org/10.1016/0165-1684(94)00102-6

    Article  MATH  Google Scholar 

  15. Kirszenberg, A., Tochon, G., Puybareau, É., Angulo, J.: Going beyond p-convolutions to learn grayscale morphological operators. In: Lect Notes Comput Sc. vol. 12708, pp. 470–482. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-76657-3_34

  16. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015). https://doi.org/10.1038/nature14539

    Article  Google Scholar 

  17. Masci, J., Angulo, J., Schmidhuber, J.: A learning framework for morphological operators using counter-harmonic mean. In: Lect Notes Comput Sc. vol. 7883, pp. 329–340. Springer, Berlin, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38294-9_28

  18. Mellouli, D., Hamdani, T.M., Ayed, M.B., Alimi, A.M.: Morph-CNN: A morphological convolutional neural network for image classification. In: Lect Notes Comput Sc. vol. 10635, pp. 110–117. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-70096-0_12

  19. Mondal, R., Dey, M.S., Chanda, B.: Image restoration by learning morphological opening-closing network. Mathematical Morphology - Theory and Applications 4(1), 87–107 (2020). https://doi.org/10.1515/mathm-2020-0103

    Article  MATH  Google Scholar 

  20. Mondal, R., Mukherjee, S.S., Santra, S., Chanda, B.: Morphological Network: How Far Can We Go with Morphological Neurons? (2019). https://doi.org/10.48550/arxiv.1901.00109

  21. Mondal, R., Santra, S., Chanda, B.: Dense morphological network: An universal function approximator. CoRR (2019), https://arxiv.org/abs/1901.00109

  22. Moya-Sánchez, E.U., Xambó-Descamps, S., Sánchez Pérez, A., Salazar-Colores, S., et al.: A bio-inspired quaternion local phase CNN layer with contrast invariance and linear sensitivity to rotation angles. Pattern Recognition Letters 131, 56–62 (2020). https://doi.org/10.1016/j.patrec.2019.12.001

    Article  Google Scholar 

  23. Nogueira, K., Chanussot, J., Mura, M.D., Santos, J.A.D.: An introduction to deep morphological networks. IEEE Access 9, 114308–114324 (2021). https://doi.org/10.1109/ACCESS.2021.3104405

    Article  Google Scholar 

  24. Noyel, G.: Logarithmic mathematical morphology: A new framework adaptive to illumination changes. Lect Notes Comput Sc, vol. 11401, pp. 453–461. Springer (2019). https://doi.org/10.1007/978-3-030-13469-3_53

  25. Noyel, G.: Morphological and logarithmic analysis of large image databases. Dissertation of accreditation to supervise research, Université de Reims Champagne-Ardenne, France (Jun 2021), https://tel.archives-ouvertes.fr/tel-03343079

  26. Noyel, G., Jourlin, M.: Double-sided probing by map of Asplund’s distances using logarithmic image processing in the framework of mathematical morphology. Lect Notes Comput Sc, vol. 10225, pp. 408–420. Springer (2017). https://doi.org/10.1007/978-3-319-57240-6_33

  27. Noyel, G., Jourlin, M.: Functional asplund metrics for pattern matching, robust to variable lighting conditions. Image Anal. Stereol. 39(2), 53–71 (2020). https://doi.org/10.5566/ias.2292

    Article  MathSciNet  MATH  Google Scholar 

  28. Pinoli, J.C.: Metrics, scalar product and correlation adapted to logarithmic images. Acta Stereologica 11(2), 157–168 (1992), https://popups.uliege.be:443/0351-580x/index.php?id=1901

  29. Saeedan, F., Weber, N., Goesele, M., Roth, S.: Detail-preserving pooling in deep networks. In: CVPR 2018. pp. 9108–9116 (2018). https://doi.org/10.1109/CVPR.2018.00949

  30. Serra, J.: Image Analysis and Mathematical Morphology, vol. 1. Academic, Orlando, FL, USA (1982)

    MATH  Google Scholar 

  31. Shen, Y., Zhong, X., Shih, F.Y.: Deep morphological neural networks. CoRR (2019), https://arxiv.org/abs/1909.01532

  32. Velasco-Forero, S., Pagès, R., Angulo, J.: Learnable empirical mode decomposition based on mathematical morphology. SIAM J. Imaging Sci. 15(1), 23–44 (2022). https://doi.org/10.1137/21M1417867

    Article  MathSciNet  MATH  Google Scholar 

  33. Zalando: Fashion MNIST. https://www.kaggle.com/datasets/zalando-research/fashionmnist (2017)

  34. Zhang, W., Zhao, X., Morvan, J.M., Chen, L.: Improving shadow suppression for illumination robust face recognition. IEEE T Pattern Anal 41(3), 611–624 (2019). https://doi.org/10.1109/TPAMI.2018.2803179

    Article  Google Scholar 

  35. 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: Lect Notes Comput Sc. vol. 11564, pp. 310–322. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20867-7_24

Download references

Author information

Authors and Affiliations

  1. Laboratoire Hubert Curien, UMR CNRS 5516, Université Jean Monnet, 42 000, Saint-Etienne, France

    Guillaume Noyel, Emile Barbier-Renard, Michel Jourlin & Thierry Fournel

Authors
  1. Guillaume Noyel
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Emile Barbier-Renard
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Michel Jourlin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Thierry Fournel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Guillaume Noyel .

Editor information

Editors and Affiliations

  1. University of Strasbourg, Strasbourg, France

    Étienne Baudrier

  2. University of Strasbourg, Strasbourg, France

    Benoît Naegel

  3. University of Strasbourg, Strasbourg, France

    Adrien Krähenbühl

  4. University of Strasbourg, Strasbourg, France

    Mohamed Tajine

Rights and permissions

Reprints and permissions

Copyright information

© 2022 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Noyel, G., Barbier-Renard, E., Jourlin, M., Fournel, T. (2022). Logarithmic Morphological Neural Nets Robust to Lighting Variations. In: Baudrier, É., Naegel, B., Krähenbühl, A., Tajine, M. (eds) Discrete Geometry and Mathematical Morphology. DGMM 2022. Lecture Notes in Computer Science, vol 13493. Springer, Cham. https://doi.org/10.1007/978-3-031-19897-7_36

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19897-7_36

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19896-0

  • Online ISBN: 978-3-031-19897-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation