iBet uBet web content aggregator. Adding the entire web to your favor.
iBet uBet web content aggregator. Adding the entire web to your favor.



Link to original content: https://doi.org/10.1007/s00521-023-08639-1
DeepGCSS: a robust and explainable contour classifier providing generalized curvature scale space features | Neural Computing and Applications Skip to main content

Advertisement

Springer Nature Link
Log in

DeepGCSS: a robust and explainable contour classifier providing generalized curvature scale space features

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

In this paper, we build a novel, robust, and explainable deep neural network architecture for contour classification whose feature extraction layers are a deep version of the Generalized CSS (Generalized Curvature Scale Space) descriptors. For particular kernels, the proposed model behaves exactly like GCSS when extracting areas with strong curvatures. Such architecture is firstly essential to establish a comparison between the efficiency of hand-crafted kernels and the learned ones and secondly to study the ability of the classifier to map the input data into an invariant representation. Experimental results on MPEG-7 and MNIST contour datasets prove that the feature extraction block with hand-crafted kernels leads to an invariant and explainable CSS-based representation. Even though the number of parameters in the DeepGCSS model is much smaller compared to the conventional contour classifiers, the performance remains close. The robustness study was carried out using the ContourVerifier and proves that the features extraction block with hand-crafted kernels leads to a more robust GCSS-based representation model.

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

Similar content being viewed by others

Explore related subjects

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

Data availibility

All analyzed data during this study are available in the following Github repository: https://github.com/OueslatiRania/2D-contours-dataset. Generated models are available on request.

Notes

  1. Different applications are available in the following Github https://github.com/topics/curvature-scale-space.

  2. Available in the following Github http://yann.lecun.com/exdb/mnist/.

References

  1. Mokhtarian F, Abbasi S, Kittler J (1996) Robust and efficient shape indexing through curvature scale space. In: British machine vision conference. Citeseer

  2. Kim W-Y, Kim Y-S (2000) A region-based shape descriptor using zernike moments. Signal Proc Image Commun 16(1–2):95–102

    Article  Google Scholar 

  3. Hu M-K (1962) Visual pattern recognition by moment invariants. IRE Trans Inform Theory 8(2):179–187

    Article  MATH  Google Scholar 

  4. Ghorbel F, Derrode S, Mezhoud R, Bannour T, Dhahbi S (2006) Image reconstruction from a complete set of similarity invariants extracted from complex moments. Pattern Recognit Lett 27(12):1361–1369

    Article  Google Scholar 

  5. Derrode S, Ghorbel F (2001) Robust and efficient fourier-mellin transform approximations for gray-level image reconstruction and complete invariant description. Comput Vis Image Underst 83(1):57–78

    Article  MATH  Google Scholar 

  6. Khotanzad A, Hong YH (1990) Invariant image recognition by zernike moments. IEEE Trans Pattern Anal Mach Intell 12(5):489–497

    Article  Google Scholar 

  7. Sheng Y, Arsenault HH (1986) Experiments on pattern recognition using invariant fourier-mellin descriptors. JOSA A 3(6):771–776

    Article  Google Scholar 

  8. Sheng Y, Duvernoy J (1986) Circular-fourier-radial-mellin transform descriptors for pattern recognition. JOSA A 3(6):885–888

    Article  Google Scholar 

  9. Sheridan P, Hintz T, Alexander D (2000) Pseudo-invariant image transformations on a hexagonal lattice. Image Vis Comput 18(11):907–917

    Article  Google Scholar 

  10. Ghorbel F (1994) A complete invariant description for gray-level images by the harmonic analysis approach. Pattern Recognit Lett 15(10):1043–1051

    Article  Google Scholar 

  11. Ghorbel F (1998) Towards a unitary formulation for invariant image description: application to image coding. In: Annales des Telecommunications, vol. 53, pp. 242–260. Springer

  12. Zhang D, Lu G (2002) Enhanced generic fourier descriptors for object-based image retrieval. In: 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 4, p. 3668. IEEE

  13. Hoffman DD, Richards WA (1984) Parts of recognition. Cognition 18(1–3):65–96

    Article  Google Scholar 

  14. Xu C, Liu J, Tang X (2008) 2d shape matching by contour flexibility. IEEE Trans Pattern Anal Mach Intell 31(1):180–186

    Google Scholar 

  15. Klassen E, Srivastava A, Mio M, Joshi SH (2004) Analysis of planar shapes using geodesic paths on shape spaces. IEEE Trans Pattern Anal Mach Intell 26(3):372–383

    Article  Google Scholar 

  16. Shu X, Wu X-J (2011) A novel contour descriptor for 2d shape matching and its application to image retrieval. Image Vis Comput 29(4):286–294

    Article  Google Scholar 

  17. Sebastian TB, Klein PN, Kimia BB (2003) On aligning curves. IEEE Trans Pattern Anal Mach Intell 25(1):116–125

    Article  Google Scholar 

  18. Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(4):509–522

    Article  Google Scholar 

  19. Ling H, Jacobs DW (2007) Shape classification using the inner-distance. IEEE Trans Pattern Anal Mach Intell 29(2):286–299

    Article  Google Scholar 

  20. Laiche N, Larabi S, Ladraa F, Khadraoui A (2014) Curve normalization for shape retrieval. Signal Proc Image Commun 29(4):556–571

    Article  Google Scholar 

  21. Kerboua-Benlarbi S, Mziou-Sallami M, Doufene A (2022) A novel gan-based system for time series generation: application to autonomous vehicles scenarios generation. In: AI and IoT for Sustainable Development in Emerging Countries, pp. 325–352. Springer

  22. Mokhtarian F, Abbasi S, Kittler J (1996) Robust and e cient shape indexing through curvature scale space. In: Proceedings of the Sixth British Machine Vision Conference, BMVC, vol. 96, p. 53. Citeseer

  23. Mokhtarian F, Abbasi S, Kittler J (1997) Efficient and robust retrieval by shape content through curvature scale space. In: Image Databases and Multi-Media Search, pp. 51–58. World Scientific

  24. Mokhtarian F, Suomela R (1998) Robust image corner detection through curvature scale space. IEEE Trans Pattern Anal Mach Intell 20(12):1376–1381

    Article  Google Scholar 

  25. Frejlichowski D (2012) Application of the curvature scale space descriptor to the problem of general shape analysis. Przeglad Elektrotechniczny 88:209–212

    Google Scholar 

  26. Sze C-J, Tyan H-R, Liao H-YM, Lu C-S, Huang S-K et al (1999) Shape-based retrieval on a fish database of Taiwan. J Appl Sci Eng 2(3):163–173

    Google Scholar 

  27. Benkhlifa A, Ghorbel F (2019) A normalized generalized curvature scale space for 2d contour representation. In: Representations, Analysis and Recognition of Shape and Motion from Imaging Data: 7th International Workshop, RFMI 2017, Savoie, France, December 17–20, 2017, Revised Selected Papers 7, pp. 167–177. Springer

  28. Jalba AC, Wilkinson MH, Roerdink JB (2006) Shape representation and recognition through morphological curvature scale spaces. IEEE Trans Image Proces 15(2):331–341

    Article  Google Scholar 

  29. Agarwal G, K Goel S Object Recognition through Curvature Scale Space. http://home.iitk.ac.in/~amit/courses/768/99/gunjan/. [Online; accessed 11-April-2023]

  30. BenKhlifa A, Ghorbel F (2019) An almost complete curvature scale space representation: Euclidean case. Signal Process Image Commun 75:32–43

    Article  Google Scholar 

  31. Ratanamahatana CA, Keogh E (2004) Everything you know about dynamic time warping is wrong. In: Third Workshop on Mining Temporal and Sequential Data, vol. 32. Citeseer

  32. Ramesh B, Xiang C, Lee TH (2015) Shape classification using invariant features and contextual information in the bag-of-words model. Pattern Recognit 48(3):894–906

    Article  Google Scholar 

  33. Wang X, Feng B, Bai X, Liu W, Latecki LJ (2014) Bag of contour fragments for robust shape classification. Pattern Recognit 47(6):2116–2125

    Article  Google Scholar 

  34. Shen W, Jiang Y, Gao W, Zeng D, Wang X (2016) Shape recognition by bag of skeleton-associated contour parts. Pattern Recognit Lett 83:321–329

    Article  Google Scholar 

  35. Li C, Stevens A, Chen C, Pu Y, Gan Z, Carin L (2016) Learning weight uncertainty with stochastic gradient mcmc for shape classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5666–5675

  36. Wang J, Bai X, You X, Liu W, Latecki LJ (2012) Shape matching and classification using height functions. Pattern Recognit Lett 33(2):134–143

    Article  Google Scholar 

  37. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inform Process Syst 25:1097–1105

    Google Scholar 

  38. Droby A, El-Sana J (2021) Contourcnn: Convolutional neural network for contour data classification. In: 2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), pp. 1–7. IEEE

  39. Khalsi R, Sallami M, Smati I, Ghorbel F (2022) Contourverifier: A novel system for the robustness evaluation of deep contour classifiers. In: Proceedings of the 14th International Conference on Agents and Artificial Intelligence, vol. 3, pp. 1003–1010

  40. Adjed F, Mziou Sallami M, Taima A (2022) Abstract interpretation limitations for deep neural network robustness evaluation. In: Traitement & Analyse de L’information Methodes et Applications, pp. 68–76

  41. Arrieta AB, Díaz-Rodríguez N, Del Ser J, Bennetot A, Tabik S, Barbado A, García S, Gil-López S, Molina D, Benjamins R et al (2020) Explainable artificial intelligence (xai): concepts, taxonomies, opportunities and challenges toward responsible ai. Inform Fus 58:82–115

    Article  Google Scholar 

  42. Bai X, Wang X, Liu X, Liu Q, Song J, Sebe N, Kim B (2021) Explainable deep learning for efficient and robust pattern recognition: a survey of recent developments. Pattern Recognit 120:108102

    Article  Google Scholar 

  43. Singh RK, Pandey R, Babu RN (2021) Covidscreen: explainable deep learning framework for differential diagnosis of covid-19 using chest x-rays. Neural Comput Appl 33(14):8871–8892

    Article  Google Scholar 

  44. Adjed F, Mziou-Sallami M, Pelliccia F, Rezzoug M, Schott L, Bohn C, Jaafra Y (2022) Coupling algebraic topology theory, formal methods and safety requirements toward a new coverage metric for artificial intelligence models. Neural Computing and Applications, 1–16

  45. Mziou-Sallami M, Adjed F (2022) Towards a certification of deep image classifiers against convolutional attacks. In: ICAART (2), pp. 419–428

  46. Mziou Sallami M, Ibn Khedher M, Trabelsi A, Kerboua-Benlarbi S, Bettebghor D (2019) Safety and robustness of deep neural networks object recognition under generic attacks. In: International Conference on Neural Information Processing, pp. 274–286. Springer

  47. Velich R, Kimmel R (2022) Deep signatures–learning invariants of planar curves. arXiv preprint arXiv:2202.05922

  48. Hssayeni MD, Saxena S, Ptucha R, Savakis A (2017) Distracted driver detection: deep learning vs handcrafted features. Electron Imaging 2017(10):20–26

    Article  Google Scholar 

  49. Côté-Allard U, Campbell E, Phinyomark A, Laviolette F, Gosselin B, Scheme E (2020) Interpreting deep learning features for myoelectric control: a comparison with handcrafted features. Front Bioeng Biotech 8:158

    Article  Google Scholar 

  50. Nanni L, Ghidoni S, Brahnam S (2017) Handcrafted vs. non-handcrafted features for computer vision classification. Pattern Recognit 71:158–172. https://doi.org/10.1016/j.patcog.2017.05.025

    Article  Google Scholar 

  51. Georgescu M-I, Ionescu RT, Popescu M (2019) Local learning with deep and handcrafted features for facial expression recognition. IEEE Access 7:64827–64836

    Article  Google Scholar 

  52. Mokhtarian F, Abbasi S (2001) Affine curvature scale space with affine length parametrisation. Pattern Analysis & Applications 4:1–8

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Author notes

  1. Mallek Mziou-Sallami and Rania Khalsi have contributed equally to this work.

Authors and Affiliations

  1. CEA, The French Alternative Energies and Atomic Energy Commission, 2 Rue Gaston Cremieux, 91000, Évry-Courcouronnes, France

    Mallek Mziou-Sallami

  2. CRISTAL Laboratory, GRIFT Research Group, Ecole Nationale des Sciences de l’Informatique (ENSI), La Manouba University, 2010, La Manouba, Tunisia

    Rania Khalsi, Imen Smati, Slim Mhiri & Faouzi Ghorbel

Authors
  1. Mallek Mziou-Sallami
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rania Khalsi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Imen Smati
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Slim Mhiri
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Faouzi Ghorbel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Mallek Mziou-Sallami or Rania Khalsi.

Ethics declarations

Conflict of interest

The authors have no competing relevant interest to declare about the content of this article.

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 (e.g. a society or other partner) 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

Mziou-Sallami, M., Khalsi, R., Smati, I. et al. DeepGCSS: a robust and explainable contour classifier providing generalized curvature scale space features. Neural Comput & Applic 35, 17689–17700 (2023). https://doi.org/10.1007/s00521-023-08639-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-023-08639-1

Keywords

Search

Navigation