Skip to main content
SpringerLink
Log in

Evaluating the Informativity of a Training Sample for Image Classification by Deep Learning Methods

  • Published:
Cybernetics and Systems Analysis Aims and scope

Abstract

A new approach to evaluating the informativity of a training sample when recognizing images obtained by means of remote sensing is proposed. It is shown that the informativity of a training sample can be represented by a set of characteristics, where each of them describes certain data properties. A dependence between the training sample characteristics and the accuracy of the classifier trained on the basis of this sample is established. The proposed approach is applied to various test training samples and their evaluation results are presented. When evaluating the training sample using the new approach, the process is shown to be much faster than that of training a neural network. This allows us to use the proposed approach for the preliminary estimation of a training sample in the problems of image recognition by deep learning methods.

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

Similar content being viewed by others

References

  1. A. Khan, A. Sohail, U. Zahoora, and A. Qureshi, “A survey of the recent architectures of deep convolutional neural networks,” Artif. Intell. Rev., Vol. 53, Iss. 8. 5455–5516 (2020). 10.1007/s10462-020-09825-6.

  2. B. P. Rusyn, V. A. Tayanov, and O. A. Lutsyk, “Upper-bound estimates for classifiers based on a dissimilarity function,” Cybern. Syst. Analysis, Vol. 48, No. 4, 592–600 (2012). 10.1007/s10559-012-9439-2.

  3. V. P. Boyun, “The principles of organizing the search for an object in an image, tracking an object and the selection of informative features based on the visual perception of a person,” in: S. Babichev, D. Peleshko, O. Vynokurova (eds.), Data Stream Mining & Processing (DSMP 2020), Communications in Computer and Information Science, Vol. 1158, Springer, Cham (2020), pp. 22–44. 10.1007/978-3-030-61656-4_2.

  4. V. Vapnik, The Nature of Statistical Learning Theory, Springer-Verlag, New York (2000).

  5. C. M. Bishop, Pattern Recognition and Machine Learning, Springer-Verlag, New York (2006).

  6. Y. Chen, Z. Lin, X. Zhao, G. Wang, and Y. Gu, “Deep learning-based classification of hyperspectral data,” IEEE J. of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 7, Iss. 6, 2094–2107 (2014). 10.1109/JSTARS.2014.2329330.

  7. L. Ma, Y. Liu, X. Zhang, Y. Ye, G. Yin, and B. A. Johnson, “Deep learning in remote sensing applications: A meta-analysis and review,” ISPRS J. of Photogrammetry and Remote Sensing, Vol. 152, 166–177 (2019). 10.1016/j.isprsjprs.2019.04.015.

  8. Y. Li, H. Zhang, X. Xue, Y. Jiang, and Q. Shen, “Deep learning for remote sensing image classification: A survey,” WIREs Data Mining Knowl. Discov., Vol. 8, Iss. 6 (2018). 10.1002/widm.1264.

  9. G. Cheng, X. Xie, J. Han, L. Guo, and G. Xia, “Remote sensing image scene classification meets deep learning: challenges, methods, benchmarks, and opportunities,” IEEE J. of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 13, 3735–3756 (2020). 10.1109/JSTARS.2020.3005403.

  10. M. Hoque, R. Burks, C. Kwan, J. Li, “Deep learning for remote sensing image super-resolution,” in: Proc. 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conf. (UEMCON) (New York, NY, USA, 10–12 Oct, 2019), IEEE (2019), pp. 286–292. 10.1109/UEMCON47517.2019.8993047.

  11. T. G. Van Niel, T.R. McVicar, and B. Datt, “On the relationship between training sample size and data dimensionality: Monte Carlo analysis of broadband multi-temporal classification,” Remote Sensing of Environment, Vol. 98, Iss. 4, 468–480 (2005). 10.1016/j.rse.2005.08.011.

  12. Q. Zou, L. Ni, T. Zhang, and Q. Wang, “Deep learning based feature selection for remote sensing scene classification,” IEEE Geoscience and Remote Sensing Letters, Vol. 12, Iss. 11, 2321–2325 (2015). 10.1109/LGRS.2015.2475299.

  13. S. Hinterstoisser, V. Lepetit, P. Wohlhart, and K. Konolige, “On pre-trained image features and synthetic images for deep learning,” in: L. Leal-Taix_ and S. Roth (eds.), Computer Vision — ECCV 2018 Workshops, ECCV 2018; Lecture Notes in Computer Science, Vol. 11129, Springer, Cham (2018), pp 682–697. 10.1007/978-3-030-11009-3_42.

  14. B. Genc, and H. Tunc, , “Optimal training and test sets design for machine learning,” Turk. J. Elec. Eng. & Comp. Sci., Vol. 27, 1534–1545 (2019). 10.3906/elk-1807-212.

  15. S. Dodge and L. Karam, “Understanding how image quality affects deep neural networks,” in: Proc. 2016 Eighth Intern. Conf. on Quality of Multimedia Experience (Lisbon, Portugal, 6–8 June, 2016), IEEE (2016). 10.1109/QoMEX.2016.7498955.

  16. G. Cheng, C. Yang, X. Yao, L. Guo, and J. Han, “When deep learning meets metric learning: Remote sensing image scene classification via learning discriminative CNNs,” IEEE Trans. on Geoscience and Remote Sensing, Vol. 56, No. 5, 2811–2821 (2018). 10.1109/TGRS.2017.2783902.

  17. X. Ma, J. Geng, and H. Wang, “Hyperspectral image classification via contextual deep learning,” J. Image Video Proc. 2015, Article Number 20 (2015). 10.1186/s13640-015-0071-8.

  18. S. A. Subbotin, “The training set quality measures for neural network learning,” Opt. Mem. Neural Networks, Vol. 19, Iss. 2, 126–139 (2010). 10.3103/S1060992X10020037.

  19. R. Forsati, A. Moayedikia, and B. Safarkhani, “Heuristic approach to solve feature selection problem,” in: H. Cherifi, J. M. Zain, and E. El-Qawasmeh (eds.), Digital Information and Communication Technology and Its Applications, DICTAP 2011; Communications in Computer and Information Science, Vol. 167, Springer, Berlin–Heidelberg (2011), pp. 707–717. 10.1007/978-3-642-22027-2_59.

  20. K. Huang and S. Aviyente, “Wavelet feature selection for image classification,” IEEE Trans. on Image Processing, Vol. 17, Iss. 9, 1709–1720 (2008). 10.1109/TIP.2008.2001050.

  21. J. Muschelli, “ROC and AUC with a binary predictor: A potentially misleading metric,” J. Classif., Vol. 37, Iss. 3, 696–708 (2020). 10.1007/s00357-019-09345-1.

  22. D. I. Belov and R. D. Armstrong, “Distributions of the Kullback–Leibler divergence with applications,” British J. of Mathematical and Statistical Psychology, Vol. 64, Iss. 2, 291–309 (2011). 10.1348/000711010X522227.

  23. R. C. Prati, G. E. A. P. A. Batista, M. C. Monard, “Class imbalances versus class overlapping: An analysis of a learning system behavior,” in: R. Monroy, G. Arroyo-Figueroa, L. E. Sucar, and H. Sossa (eds.), MICAI 2004: Advances in Artificial Intelligence, MICAI 2004; Lecture Notes in Computer Science, Vol. 2972, Springer, Berlin–Heidelberg (2004), pp. 312–321. 10.1007/978-3-540-24694-7_32.

  24. M. Shepperd and M. Cartwright, “Predicting with sparse data,” in: Proc. 7th IEEE Intern. Software Metrics Symp. (London, UK, 4–6 April, 2001), IEEE (2001), pp. 28–39. 10.1109/METRIC.2001.915513.

Download references

Author information

Authors and Affiliations

  1. Karpenko Physico-Mechanical Institute, National Academy of Sciences of Ukraine, Lviv, Ukraine

    B. P. Rusyn, O. A. Lutsyk & R. Y. Kosarevych

Authors
  1. B. P. Rusyn
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. O. A. Lutsyk
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. R. Y. Kosarevych
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to B. P. Rusyn.

Additional information

Translated from Kibernetyka ta Systemnyi Analiz, No. 6, November–December, 2021, pp. 13–24.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rusyn, B.P., Lutsyk, O.A. & Kosarevych, R.Y. Evaluating the Informativity of a Training Sample for Image Classification by Deep Learning Methods. Cybern Syst Anal 57, 853–863 (2021). https://doi.org/10.1007/s10559-021-00411-4

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10559-021-00411-4

Keywords

Search

Navigation