Fuzzy Sets: A Key Towards Hybrid Explainable Artificial Intelligence for Image Understanding | SpringerLink
Skip to main content
Springer Nature Link
Log in

Fuzzy Sets: A Key Towards Hybrid Explainable Artificial Intelligence for Image Understanding

  • Conference paper
  • First Online:
Fuzzy Logic and Technology, and Aggregation Operators (EUSFLAT 2023, AGOP 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14069))

  • 605 Accesses

Abstract

In this paper, we propose a basis for discussing the role of fuzzy sets theory in the context of explainable artificial intelligence. We advocate that combining several frameworks in artificial intelligence, including fuzzy sets theory, adopting a hybrid point of view both for knowledge and data representation and for reasoning, offers opportunities towards explainability. This idea is instantiated on the example of image understanding, expressed as a spatial reasoning problem.

I. Bloch—This work was partly supported by the author’s chair in Artificial Intelligence (Sorbonne Université and SCAI). A part of the work was performed while the author was with LTCI, Télécom Paris, Institut Polytechnique de Paris.

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
¥17,985 /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
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 11210
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 14013
Price includes VAT (Japan)
  • 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

Similar content being viewed by others

Notes

  1. 1.

    These are only examples and similar approaches have been developed in other application domains, such as satellite imaging, video, music representations, etc.

References

  1. Aiello, M., Pratt-Hartmann, I., van Benthem, J. (eds.): Handbook of Spatial Logic. Springer, Dordrecht (2007). https://doi.org/10.1007/978-1-4020-5587-4

    Book  Google Scholar 

  2. Aiguier, M., Atif, J., Bloch, I., Pino Pérez, R.: Explanatory relations in arbitrary logics based on satisfaction systems, cutting and retraction. Int. J. Approximate Reasoning 102, 1–20 (2018)

    Article  MathSciNet  MATH  Google Scholar 

  3. Aiguier, M., Bloch, I.: Logical dual concepts based on mathematical morphology in stratified institutions. J. Appl. Non-Classical Log. 29(4), 392–429 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  4. Aldea, E., Bloch, I.: Toward a better integration of spatial relations in learning with graphical models. In: Guillet, F., Ritschard, G., Zighed, D.A., Briand, H. (eds.) Advances in Knowledge Discovery and Management. SCI, vol. 292, pp. 77–94. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-00580-0_5

    Chapter  MATH  Google Scholar 

  5. Atif, J., Hudelot, C., Bloch, I.: Explanatory reasoning for image understanding using formal concept analysis and description logics. IEEE Trans. Syst. Man Cybern. Syst. 44(5), 552–570 (2014)

    Article  Google Scholar 

  6. Atif, J., Hudelot, C., Fouquier, G., Bloch, I., Angelini, E.: From generic knowledge to specific reasoning for medical image interpretation using graph-based representations. In: International Joint Conference on Artificial Intelligence, IJCAI 2007, Hyderabad, India, pp. 224–229 (2007)

    Google Scholar 

  7. Bloch, I.: Information combination operators for data fusion: a comparative review with classification. IEEE Trans. Syst. Man Cybern. 26(1), 52–67 (1996)

    Article  MathSciNet  Google Scholar 

  8. Bloch, I.: On fuzzy spatial distances. In: Hawkes, P. (ed.) Advances in Imaging and Electron Physics, vol. 128, pp. 51–122. Elsevier, Amsterdam (2003)

    Google Scholar 

  9. Bloch, I.: Spatial reasoning under imprecision using fuzzy set theory, formal logics and mathematical morphology. Int. J. Approximate Reasoning 41(2), 77–95 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  10. Bloch, I.: Fuzzy sets for image processing and understanding. Fuzzy Sets Syst. 281, 280–291 (2015)

    Article  MathSciNet  MATH  Google Scholar 

  11. Bloch, I.: Mathematical morphology and spatial reasoning: fuzzy and bipolar setting. TWMS J. Pure Appl. Math. 12(1), 104–125 (2021). Special Issue on Fuzzy Sets in Dealing with Imprecision and Uncertainty: Past and Future Dedicated to the Memory of Lotfi A. Zadeh

    MathSciNet  MATH  Google Scholar 

  12. Bloch, I.: Modeling imprecise and bipolar algebraic and topological relations using morphological dilations. Math. Morphol. Theory Appl. 5(1), 1–20 (2021)

    MATH  Google Scholar 

  13. Bloch, I.: Hybrid artificial intelligence for knowledge representation and model-based medical image understanding - towards explainability. In: Baudrier, É., Naegel, B., Krähenbühl, A., Tajine, M. (eds.) DGMM 2022. LNCS, vol. 13493, pp. 17–25. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19897-7_2

    Chapter  Google Scholar 

  14. Bloch, I., Atif, J.: Defining and computing Hausdorff distances between distributions on the real line and on the circle: link between optimal transport and morphological dilations. Math. Morphol. Theory Appl. 1(1), 79–99 (2016)

    MATH  Google Scholar 

  15. Bloch, I., Géraud, T., Maître, H.: Representation and fusion of heterogeneous fuzzy information in the 3D space for model-based structural recognition - application to 3D brain imaging. Artif. Intell. 148, 141–175 (2003)

    Article  MathSciNet  MATH  Google Scholar 

  16. Bloch, I., Lang, J., Pérez, R.P., Uzcátegui, C.: Morphologic for knowledge dynamics: revision, fusion, abduction. Technical report. arXiv:1802.05142, arXiv cs.AI (2018)

  17. Bloch, I., Ralescu, A.: Fuzzy Sets Methods in Image Processing and Understanding: Medical Imaging Applications. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-19425-2

    Book  Google Scholar 

  18. Bloch, I., Lesot, M.J.: Towards a formulation of fuzzy contrastive explanations. In: IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 1–8 (2022)

    Google Scholar 

  19. Bouchon-Meunier, B., Lesot, M.J., Marsala, C.: Lotfi A. Zadeh, the visionary in explainable artificial intelligence. TWMS J. Pure Appl. Math. 12(1), 5–13 (2021)

    MathSciNet  MATH  Google Scholar 

  20. Cesar, R., Bengoetxea, E., Bloch, I., Larranaga, P.: Inexact graph matching for model-based recognition: evaluation and comparison of optimization algorithms. Pattern Recogn. 38, 2099–2113 (2005)

    Article  Google Scholar 

  21. Chopin, J., Fasquel, J.B., Mouchère, H., Dahyot, R., Bloch, I.: Improving semantic segmentation with graph-based structural knowledge. In: El Yacoubi, M., Granger, E., Yuen, P.C., Pal, U., Vincent, N. (eds.) ICPRAI 2022. LNCS, vol. 13363, pp. 173–184. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-09037-0_15

    Chapter  Google Scholar 

  22. Colliot, O., Camara, O., Bloch, I.: Integration of fuzzy spatial relations in deformable models - application to brain MRI segmentation. Pattern Recogn. 39, 1401–1414 (2006)

    Article  Google Scholar 

  23. Coradeschi, S., Saffiotti, A.: Anchoring symbols to vision data by fuzzy logic. In: Hunter, A., Parsons, S. (eds.) ECSQARU 1999. LNCS (LNAI), vol. 1638, pp. 104–115. Springer, Heidelberg (1999). https://doi.org/10.1007/3-540-48747-6_10

    Chapter  Google Scholar 

  24. Coste-Marquis, S., Marquis, P.: From explanations to intelligible explanations. In: 1st International Workshop on Explainable Logic-Based Knowledge Representation (XLoKR 2020) (2020)

    Google Scholar 

  25. Couteaux, V., et al.: Automatic knee meniscus tear detection and orientation classification with Mask-RCNN. Diagn. Interv. Imaging 100, 235–242 (2019)

    Article  Google Scholar 

  26. De Raedt, L., Dumancic, S., Manhaeve, R., Marra, G.: From statistical relational to neuro-symbolic artificial intelligence. In: Bessiere, C. (ed.) Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-2020, pp. 4943–4950 (2020)

    Google Scholar 

  27. Delmonte, A., Mercier, C., Pallud, J., Bloch, I., Gori, P.: White matter multi-resolution segmentation using fuzzy set theory. In: IEEE International Symposium on Biomedical Imaging (ISBI), Venice, Italy, pp. 459–462 (2019)

    Google Scholar 

  28. Denis, C., Varenne, F.: Interprétabilité et explicabilité de phénomènes prédits par de l’apprentissage machine. Revue Ouverte d’Intelligence Artificielle 3, 287–310 (2022)

    Article  Google Scholar 

  29. Deruyver, A., Hodé, Y.: Constraint satisfaction problem with bilevel constraint: application to interpretation of over-segmented images. Artif. Intell. 93(1–2), 321–335 (1997)

    Article  MathSciNet  MATH  Google Scholar 

  30. Dubois, D., Prade, H.: A review of fuzzy set aggregation connectives. Inf. Sci. 36, 85–121 (1985)

    Article  MathSciNet  MATH  Google Scholar 

  31. Fasquel, J., Delanoue, N.: A graph based image interpretation method using a priori qualitative inclusion and photometric relationships. IEEE Trans. Pattern Anal. Mach. Intell. 41(5), 1043–1055 (2019)

    Article  Google Scholar 

  32. Fouquier, G., Atif, J., Bloch, I.: Sequential model-based segmentation and recognition of image structures driven by visual features and spatial relations. Comput. Vis. Image Underst. 116(1), 146–165 (2012)

    Article  Google Scholar 

  33. Freeman, J.: The modelling of spatial relations. Comput. Graph. Image Process. 4(2), 156–171 (1975)

    Article  Google Scholar 

  34. d’Avila Garcez, A., Lamb, L.C.: Neurosymbolic AI: the 3rd wave. CoRR abs/2012.05876 (2020)

    Google Scholar 

  35. Garnelo, M., Shanahan, M.: Reconciling deep learning with symbolic artificial intelligence: representing objects and relations. Curr. Opin. Behav. Sci. 29, 17–23 (2019)

    Article  Google Scholar 

  36. Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach. Part I: causes. Br. J. Philos. Sci. 56(4), 843–887 (2005)

    Article  MATH  Google Scholar 

  37. Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach. Part II: explanations. Br. J. Philos. Sci. 56(4), 889–911 (2005)

    Article  MATH  Google Scholar 

  38. Harnad, S.: The symbol grounding problem. Physica 42, 335–346 (1990)

    Google Scholar 

  39. Hudelot, C., Atif, J., Bloch, I.: Fuzzy spatial relation ontology for image interpretation. Fuzzy Sets Syst. 159, 1929–1951 (2008)

    Article  MathSciNet  Google Scholar 

  40. Kahneman, D.: Thinking, Fast and Slow. Penguin, New York (2012)

    Google Scholar 

  41. Kautz, H.: The third AI summer: AAAI Robert S. Engelmore memorial lecture. AI Mag. 43(1), 93–104 (2022)

    Google Scholar 

  42. Landini, G., Galton, A., Randell, D., Fouad, S.: Novel applications of discrete mereotopology to mathematical morphology. Sig. Process. Image Commun. 76, 109–117 (2019)

    Article  Google Scholar 

  43. Marcus, G.: The next decade in AI: four steps towards robust artificial intelligence. CoRR abs/2002.06177 (2020)

    Google Scholar 

  44. Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  45. Miller, T.: Contrastive explanation: a structural-model approach. Knowl. Eng. Rev. 36, E14 (2021)

    Article  Google Scholar 

  46. Munro, Y., Bloch, I., Chetouani, M., Lesot, M.J., Pelachaud, C.: Argumentation and causal models in human-machine interaction: a round trip. In: 8th International Workshop on Artificial Intelligence and Cognition, Örebro, Sweden (2022)

    Google Scholar 

  47. Nempont, O., Atif, J., Bloch, I.: A constraint propagation approach to structural model based image segmentation and recognition. Inf. Sci. 246, 1–27 (2013)

    Article  MathSciNet  MATH  Google Scholar 

  48. Perchant, A., Bloch, I.: Fuzzy morphisms between graphs. Fuzzy Sets Syst. 128(2), 149–168 (2002)

    Article  MathSciNet  MATH  Google Scholar 

  49. Pierrard, R., Poli, J.P., Hudelot, C.: Spatial relation learning for explainable image classification and annotation in critical applications. Artif. Intell. 292, 103434 (2021)

    Article  MathSciNet  MATH  Google Scholar 

  50. Randell, D., Cui, Z., Cohn, A.: A spatial logic based on regions and connection. In: Nebel, B., Rich, C., Swartout, W. (eds.) Principles of Knowledge Representation and Reasoning, KR1992, pp. 165–176. Kaufmann, San Mateo (1992)

    Google Scholar 

  51. Riva, M., Gori, P., Yger, F., Bloch, I.: Is the U-Net directional-relationship aware? In: International Conference on Image Processing, Bordeaux, France, pp. 3391–3395 (2022)

    Google Scholar 

  52. Schockaert, S., De Cock, M., Cornelis, C., Kerre, E.E.: Fuzzy region connection calculus: representing vague topological information. Int. J. Approximate Reasoning 48(1), 314–331 (2008)

    Article  MathSciNet  MATH  Google Scholar 

  53. Schockaert, S., De Cock, M., Kerre, E.E.: Spatial reasoning in a fuzzy region connection calculus. Artif. Intell. 173(2), 258–298 (2009)

    Article  MathSciNet  MATH  Google Scholar 

  54. Smeulders, A., Worring, M., Santini, S., Gupta, A., Jain, R.: Content-based image retrieval at the end of the early years. IEEE Trans. Pattern Anal. Mach. Intell. 22(12), 1349–1380 (2000)

    Article  Google Scholar 

  55. Virzì, A., et al.: Segmentation of pelvic vessels in pediatric MRI using a patch-based deep learning approach. In: Melbourne, A., et al. (eds.) PIPPI/DATRA -2018. LNCS, vol. 11076, pp. 97–106. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00807-9_10

    Chapter  Google Scholar 

  56. Xie, X., Niu, J., Liu, X., Chen, Z., Tang, S., Yu, S.: A survey on incorporating domain knowledge into deep learning for medical image analysis. Med. Image Anal. 69, 101985 (2021)

    Article  Google Scholar 

  57. Yager, R.R.: Connectives and quantifiers in fuzzy sets. Fuzzy Sets Syst. 40, 39–75 (1991)

    Article  MathSciNet  MATH  Google Scholar 

  58. Yang, Y., Atif, J., Bloch, I.: Abductive reasoning using tableau methods for high-level image interpretation. In: Hölldobler, S., Krötzsch, M., Peñaloza, R., Rudolph, S. (eds.) KI 2015. LNCS (LNAI), vol. 9324, pp. 356–365. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24489-1_34

    Chapter  Google Scholar 

  59. Zadeh, L.A.: Fuzzy sets. Inf. Control 8, 338–353 (1965)

    Article  MATH  Google Scholar 

  60. Zadeh, L.A.: The concept of a linguistic variable and its application to approximate reasoning. Inf. Sci. 8, 199–249 (1975)

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

The author would like to thank all her co-authors, and to emphasize that the ideas summarized in this paper benefitted from many joint works with PhD candidates, post-doctoral researchers, colleagues in universities and research centers in several countries, with university hospitals, and with industrial partners.

Author information

Authors and Affiliations

  1. Sorbonne Université, CNRS, LIP6, Paris, France

    Isabelle Bloch

Authors
  1. Isabelle Bloch
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Isabelle Bloch .

Editor information

Editors and Affiliations

  1. University of the Balearic Islands, Palma, Spain

    Sebastia Massanet

  2. University of Oviedo, Gijón, Spain

    Susana Montes

  3. University of the Balearic Islands, Palma, Spain

    Daniel Ruiz-Aguilera

  4. University of the Balearic Islands, Palma, Spain

    Manuel González-Hidalgo

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Bloch, I. (2023). Fuzzy Sets: A Key Towards Hybrid Explainable Artificial Intelligence for Image Understanding. In: Massanet, S., Montes, S., Ruiz-Aguilera, D., González-Hidalgo, M. (eds) Fuzzy Logic and Technology, and Aggregation Operators. EUSFLAT AGOP 2023 2023. Lecture Notes in Computer Science, vol 14069. Springer, Cham. https://doi.org/10.1007/978-3-031-39965-7_39

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-39965-7_39

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-39964-0

  • Online ISBN: 978-3-031-39965-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics