Advertisement

Logo and Brand Recognition from Imbalanced Dataset Using MiniGoogLeNet and MiniVGGNet Models

  • SarwoEmail author
  • Yaya Heryadi
  • Widodo Budiharto
  • Edi Abdurachman
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11431)

Abstract

Deep learning model tends to promote models with deep structure. Despite its high accuracy, the model was not practical when high computing power was not available. Thus, deep model with not-so-deep structure or less number of model parameters is needed for low capacity computer. Logo and brand recognition task is an important and challenging problem in computer vision with wide potential applications. The inherent challenge to address this task is not only due to the presence of logo in various direction and clutters as well as imbalanced dataset but also because of high computing workload when deep learning models were adopted. This paper presents empirical results of logo recognition method using MiniVGGNet and MiniGoogleNet models combined with augmentation technique to increase variation and number of samples. The results show that the proposed model combined with augmentation technique increased accuracy of model accuracies and fasten training convergence of both models.

Keywords

Logo detection MiniVGGNet MiniGoogLeNet Augmentation technique 

Notes

Acknowledgment

This research is partially supported by Binus IntelSys Research Interest Group.

References

  1. 1.
    Samuel, A.L.: Some studies in machine learning using the game of checkers. IBM J. Res. Dev. 3(3), 210–229 (1959)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Hinton, G.E., Osindero, S., Teh, Y.-W.: Communicated by Yann Le Cun A fast learning algorithm for deep belief nets 500 units 500 units. Neural Comput. 18, 1527–1554 (2006)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Bianco, S., Buzzelli, M., Mazzini, D., Schettini, R.: Deep learning for logo recognition. Neurocomputing 245, 23–30 (2017) CrossRefGoogle Scholar
  4. 4.
    Es-Sabry, M., El Akkad, N., Merras, M., Saaidi, A., Satori, K.: Grayscale image encryption using shift bits operations. In: 2018 International Conference on Intelligent System Computer Vision, ISCV 2018, no. Figure 3, May 2018Google Scholar
  5. 5.
    Allawi, S.T., Al-A’Meri, J.H.: Image encryption based on linear feedback shift register method. In: Al-Sadiq International Conference on multidisciplinary IT Communication Technical Science and Application, AIC-MITCSA 2016, pp. 16–19 (2016)Google Scholar
  6. 6.
    Wadi, S.M., Zainal, N., Abdulgader, A.: Grey scale image hiding method based on decomposition operation. In: Proceeding - 2013 IEEE Student Conference on Research and Development, SCOReD 2013, pp. 315–318, December 2015Google Scholar
  7. 7.
    Mohanty, M., Asghar, M.R., Russello, G.: 2DCrypt: image scaling and cropping in encrypted domains. IEEE Trans. Inf. Forensics Secur. 11(11), 2542–2555 (2016)CrossRefGoogle Scholar
  8. 8.
    Owen, C.B., Makedon, F.: High quality alias free image rotation. In: Conference Record of the Thirtieth Asilomar Conference on Signals, Systems and Computers, vol. 1, pp. 115–119 (1997)Google Scholar
  9. 9.
    Barnett, S.M., Zambrini, R.: Resolution in rotation measurements. J. Mod. Opt. 53(5–6), 613–625 (2006)CrossRefGoogle Scholar
  10. 10.
    Su, H., Zhu, X., Gong, S.: Deep Learning Logo Detection with Data Expansion by Synthesising Context. CoRR, vol. abs/1612.0 (2016)Google Scholar
  11. 11.
    Kalantidis, Y., Pueyo, L.G., Trevisiol, M., van Zwol, R., Avrithis, Y.: Scalable triangulation-based logo recognition (Flickr 27). In: Proceedings of the ACM International Conference on Multimedia Retrieval (ICMR 2011), pp. 20:1–20:7 (2011)Google Scholar
  12. 12.
    Romberg, S., Clara, S.: Scalable logo recognition in real-world Images categories and subject descriptorsGoogle Scholar
  13. 13.
    Revaud, J., Schmid, C.: Correlation-Based Burstiness for Logo Retrieval Categories and Subject Descriptors: Keywords, pp. 965–968 (2012)Google Scholar
  14. 14.
    Revaud, J., et al.: DeepMatching: Hierarchical Deformable Dense Matching To cite this version: DeepMatching: Hierarchical Deformable Dense Matching (2015)Google Scholar
  15. 15.
    Romberg, S., Lienhart, R.: Bundle min-hashing for logo recognition. ACM (2013)Google Scholar
  16. 16.
    Boia, R., Bandrabur, A., Florea, C.: Local description using multi-scale complete rank transform for improved logo recognition, pp. 4–7 (2014)Google Scholar
  17. 17.
    Li, K., Chen, S., Su, S.: Logo detection with extendibility and discrimination (2013)Google Scholar
  18. 18.
    Zhang, Y., et al.: Deep learning for logo recognition. In: International Conference on Intelligent Systems Design and Applications, ISDA, vol. 245, no. 36, pp. 2051–2054 (2017)Google Scholar
  19. 19.
    Arivazhagan, N.: Logo Recognition. pp. 1–2Google Scholar
  20. 20.
    Su, H., Zhu, X., Gong, S.: Deep learning logo detection with data expansion by synthesising context. In: Proceedings of the 2017 IEEE Winter Conference Applications of Computer Vision (WACV 2017), pp. 530–539 (2017)Google Scholar
  21. 21.
    Pan, C., Yan, Z., Xu, X., Sun, M., Shao, J., Wu, D.: Learning architecture in video surveillance. pp. 123–126. IEEE (2013)Google Scholar
  22. 22.
    Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 1–9, 07–12 June 2015Google Scholar
  23. 23.
    Simonyan, K. Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations, pp. 1–14 (2015)Google Scholar
  24. 24.
    He, Z.: Deep residual learning for image recognition. arXiv.org e-Print Arch 7(3), 171–180 (2015)Google Scholar
  25. 25.
    He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision – ECCV 2016. ECCV 2016. LNCS, vol. 9908. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38CrossRefGoogle Scholar
  26. 26.
    Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, January 2017, pp. 5987–5995 (2017)Google Scholar
  27. 27.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015)Google Scholar
  28. 28.
    Pyimagesearch: Deep Learning for computer Vision using Python. Book (2017)Google Scholar
  29. 29.
    Liu, W., et al.: SSD: single shot multibox detector. arXiv, pp. 1–15 (2016)Google Scholar
  30. 30.
    Girshick, R.: Fast R-CNN. arXiv.org e-Print Arch. (2015)Google Scholar
  31. 31.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Nips, pp. 1–10 (2015)Google Scholar
  32. 32.
    Impiombato, D., et al.: You only look once: unified, real-time object detection. Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip. 794, 185–192 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Sarwo
    • 1
    Email author
  • Yaya Heryadi
    • 1
  • Widodo Budiharto
    • 1
  • Edi Abdurachman
    • 1
  1. 1.Computer Science Department, BINUS Graduate Program – Doctor of Computer ScienceBina Nusantara UniversityJakartaIndonesia

Personalised recommendations