Skip to main content
SpringerLink
Log in

Data augmentation based on shape space exploration for low-size datasets: application to 2D shape classification

  • Review
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

This article introduces a novel 2D shape data augmentation approach based on intra-class shape space exploration. The proposed method relies on a geodesic interpolation between shapes, leveraging invariant-based morphing techniques. By blending a 2D shape pair belonging to a given class, we are able to generate nonlinear augmentations, hence covering more variations within the shape space. In particular, we formulate data augmentation as an optimization problem that minimizes the deformations between two shapes using the Generalized Finite Fourier Invariant Descriptor. The proposed augmentation technique is evaluated using numerous Convolution Neural Network architectures for 2D shape classification. The results indicate the superiority of the proposed method as compared to state-of-the-art techniques when considering small-scale datasets.

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

Access this article

Log in via an institution

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
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23

Similar content being viewed by others

Data availability

The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.

References

  1. Guo Y, Liu Y, Oerlemans A, Lao S, Wu S, Lew MS (2016) Deep learning for visual understanding: a review. Neurocomputing 187:27–48

    Article  Google Scholar 

  2. Li Y, Wang S, Tian Q, Ding X (2015) Feature representation for statistical-learning-based object detection: a review. Pattern Recognit 48(11):3542–3559

    Article  Google Scholar 

  3. Paulin M, Revaud J, Harchaoui Z, Perronnin F, Schmid C (2014) Transformation pursuit for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3646–3653

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

    Article  Google Scholar 

  5. Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621

  6. Summers C, Dinneen MJ (2019) Improved mixed-example data augmentation. In: 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 1262–1270

  7. Inoue H (2018) Data augmentation by pairing samples for images classification. arXiv preprint arXiv:1801.02929

  8. Zhang H, Cisse M, Dauphin YN, Lopez-Paz D (2017) mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412

  9. Kim J-H, Choo W, Song HO (2020) Puzzle mix: exploiting saliency and local statistics for optimal mixup. In: International conference on machine learning. PMLR, pp 5275–5285

  10. Zou Y, Verma V, Mittal S, Tang WH, Pham H, Kannala J, Bengio Y, Solin A, Kawaguchi K (2023) Mixupe: understanding and improving mixup from directional derivative perspective. In: Uncertainty in artificial intelligence (2023). PMLR, pp 2597–2607

  11. Zhu J, Shi L, Yan J, Zha H (2020) Automix: mixup networks for sample interpolation via cooperative barycenter learning. In: Computer Vision–ECCV 2020: 16th European conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part X 16. Springer, pp 633–649

  12. Verma V, Lamb A, Beckham C, Najafi A, Mitliagkas I, Lopez-Paz D, Bengio Y (2019) Manifold mixup: better representations by interpolating hidden states. In: International conference on machine learning. PMLR, pp 6438–6447

  13. Kang G, Dong X, Zheng L, Yang Y (2017) Patchshuffle regularization. arXiv preprint arXiv:1707.07103

  14. Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 13001–13008

  15. Gatys LA, Ecker AS, Bethge M (2015) A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576

  16. Konno T, Iwazume M (2018) Icing on the cake: an easy and quick post-learnig method you can try after deep learning. arXiv preprint arXiv:1807.06540

  17. Bowles C, Chen L, Guerrero R, Bentley P, Gunn R, Hammers A, Dickie DA, Hernández MV, Wardlaw J, Rueckert D (2018) Gan augmentation: augmenting training data using generative adversarial networks. arXiv preprint arXiv:1810.10863 (2018)

  18. Su J, Vargas DV, Sakurai K (2019) One pixel attack for fooling deep neural networks. IEEE Trans Evolut Comput 23(5):828–841

    Article  Google Scholar 

  19. El-Sawy A, Hazem E-B, Loey M (2016) Cnn for handwritten Arabic digits recognition based on lenet-5. In: International conference on advanced intelligent systems and informatics. Springer, pp 566–575

  20. Patel V, Mujumdar N, Balasubramanian P, Marvaniya S, Mittal A (2019) Data augmentation using part analysis for shape classification. In: 2019 IEEE winter conference on applications of computer vision (WACV), pp 1223–1232. https://doi.org/10.1109/WACV.2019.00135

  21. Ciregan D, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 3642–3649

  22. Sato I, Nishimura H, Yokoi K (2015) Apac: augmented pattern classification with neural networks. arXiv preprint arXiv:1505.03229

  23. Yin D, Lopes RG, Shlens J, Cubuk ED, Gilmer J (2019) A Fourier perspective on model robustness in computer vision. arXiv preprint arXiv:1906.08988

  24. Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: delving deep into convolutional nets. arXiv preprint arXiv:1405.3531

  25. Simard PY, Steinkraus D, Platt JC et al (2003) Best practices for convolutional neural networks applied to visual document analysis. In: ICDAR, vol 3

  26. Ghorbel E, Ghorbel F, M’Hiri S (2022) A fast and efficient shape blending by stable and analytically invertible finite descriptors. IEEE Trans Image Process 31:5788–5800. https://doi.org/10.1109/TIP.2022.3199105

    Article  Google Scholar 

  27. Surazhsky T, Elber G (2002) Metamorphosis of planar parametric curves via curvature interpolation. Int J Shape Model 8(02):201–216

    Article  Google Scholar 

  28. Hirano M, Watanabe Y, Ishikawa M (2017) Rapid blending of closed curves based on curvature flow. Comput Aided Geom Design 52:217–230

    Article  MathSciNet  Google Scholar 

  29. Saba M, Schneider T, Hormann K, Scateni R (2014) Curvature-based blending of closed planar curves. Graph Models 76(5):263–272

    Article  Google Scholar 

  30. Sederberg TW, Gao P, Wang G, Mu H (1993) 2-d shape blending: an intrinsic solution to the vertex path problem. In: Proceedings of the 20th annual conference on computer graphics and interactive techniques. ACM, New York, NY, pp 15–18

  31. 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 

  32. Srivastava A, Klassen E, Joshi SH, Jermyn IH (2010) Shape analysis of elastic curves in Euclidean spaces. IEEE Trans Pattern Anal Mach Intell 33(7):1415–1428

    Article  Google Scholar 

  33. Jin L, Wen Z, Hu Z (2021) Topology-preserving nonlinear shape registration on the shape manifold. Multimed Tools Appl 80(11):17377–17389

    Article  Google Scholar 

  34. Shapira M, Rappoport A (1995) Shape blending using the star-skeleton representation. IEEE Comput Graph Appl 15(2):44–50

    Article  Google Scholar 

  35. Yang W, Feng J (2009) 2d shape morphing via automatic feature matching and hierarchical interpolation. Comput Graph 33(3):414–423

    Article  Google Scholar 

  36. Hahmann S, Bonneau G-P, Caramiaux B, Cornillac M (2007) Multiresolution morphing for planar curves. Computing 79(2):197–209

    Article  MathSciNet  Google Scholar 

  37. Yang W, Wang X, Wang G (2014) Part-to-part morphing for planar curves. Vis Comput 30(6):919–928

    Article  Google Scholar 

  38. Ghorbel E, Ghorbel F, Sakly I, M’Hiri S (2021) Fast blending of planar shapes based on invariant invertible and stable descriptors. In: 2020 25th international conference on pattern recognition (ICPR). IEEE, pp 10259–10265

  39. Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol. 34, pp 13001–13008

  40. Cubuk ED, Zoph B, Mane D, Vasudevan V, Le QV (2018) Autoaugment: learning augmentation policies from data. arXiv preprint arXiv:1805.09501

  41. Jiang X, Bunke H, Abegglen K, Kandel A (2002) Curve morphing by weighted mean of strings. In: Object recognition supported by user interaction for service robots, vol 4. IEEE, New York City at 3 Park Ave, pp 192–195

  42. Crimmins TR (1982) A complete set of Fourier descriptors for two-dimensional shapes. IEEE Trans Syst Man Cybern 12(6):848–855

    Article  MathSciNet  Google Scholar 

  43. Ghorbel F (1992) Stability of invariant fourier descriptors and its inference in the shape classification. In: International conference on pattern recognition. IEEE Computer Society Press, New York City at 3 Park Ave, pp 130–130

  44. Elghoul S, Ghorbel F (2021) A fast and robust affine-invariant method for shape registration under partial occlusion. Int J Multimed Inf Retr 11:1–21

    Google Scholar 

  45. Belogay E, Cabrelli C, Molter U, Shonkwiler R (1997) Calculating the hausdorff distance between curves. Inf Process Lett 64(1):17–22

    Article  MathSciNet  Google Scholar 

  46. Latecki LJ, Lakamper R, Eckhardt T (2000) Shape descriptors for non-rigid shapes with a single closed contour. In: Proceedings IEEE conference on computer vision and pattern recognition. CVPR 2000 (Cat. No.PR00662), vol 1. IEEE, New York City at 3 Park Ave, pp 424–4291

  47. LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541–551

    Article  Google Scholar 

  48. Yuan A, Bai G, Jiao L, Liu Y (2012) Offline handwritten English character recognition based on convolutional neural network. In: 2012 10th IAPR international workshop on document analysis systems. IEEE, New York City at 3 Park Ave, pp 125–129

  49. Ozdemir MA, Elagoz B, Alaybeyoglu A, Sadighzadeh R, Akan A (2019) Real time emotion recognition from facial expressions using CNN architecture. In: 2019 Medical technologies congress (tiptekno). IEEE, New York City at 3 Park Ave, pp 1–4

  50. Kayed M, Anter A, Mohamed H (2020) Classification of garments from fashion mnist dataset using CNN lenet-5 architecture. In: 2020 international conference on innovative trends in communication and computer engineering (ITCE). IEEE, pp 238–243

  51. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826

  52. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

  53. Sato I, Nishimura H, Yokoi K (2015) Apac: Augmented pattern classification with neural networks. arXiv preprint arXiv:1505.03229

  54. 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 

  55. 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 

  56. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556

Download references

Author information

Authors and Affiliations

  1. CRISTAL Laboratory GRIFT Group, National School of Computer Science, Manouba University, 2010, Manouba, Tunisia

    Emna Ghorbel & Faouzi Ghorbel

Authors
  1. Emna Ghorbel
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Faouzi Ghorbel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Emna Ghorbel.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

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

Ghorbel, E., Ghorbel, F. Data augmentation based on shape space exploration for low-size datasets: application to 2D shape classification. Neural Comput & Applic (2024). https://doi.org/10.1007/s00521-024-09798-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00521-024-09798-5

Keywords

Search

Navigation