Advertisement

Efficient CNN Models for Beer Bottle Cap Classification Problem

  • Quan M. TranEmail author
  • Linh V. Nguyen
  • Tai Huynh
  • Hai H. Vo
  • Vuong T. Pham
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11814)

Abstract

In this work, we present an efficient solution to the beer bottle cap classification problem. This problem arises in the Wecheer smart opener project. Although classification problem is common in Computer Vision, there is no dedicated work for beer bottle cap dataset. We combine state-of-the-art deep learning techniques to solve the problem. Our solution outperforms the well-known commercial system that is currently used by the Wecheer project. It is also more efficient than the famous architectures such as VGG, ResNet, and DenseNet for our purposes.

Keywords

Beer bottle cap Classification Deep learning Skipped connection Global Average Pooling Convolutional neural network 

Notes

Acknowledgement

We thank our colleagues, Hai Tran and Dac Dinh, for helpful discussions.

References

  1. 1.
    Volume of World Beer Production. European Beer Guide. Accessed 17 Oct 2006Google Scholar
  2. 2.
    Nelson, M.: The Barbarian’s Beverage: A History of Beer in Ancient Europe. Routledge, p. 1 (2005). ISBN 978-0-415-31121-2Google Scholar
  3. 3.
  4. 4.
    Krizhevsky, A., Sutskever, I., Hinton, G.: Advances in neural information processing systems (2012)Google Scholar
  5. 5.
    Zeiler, M.D., Fergus, R.: Visualizing and Understanding Convolutional Networks. arXiv:1311.2901 (2013)
  6. 6.
    Zhang, X., Zou, J., He, K., et al.: Accelerating Very Deep Convolutional Networks for Classification and Detection. arXiv:1505.06798 (2015)
  7. 7.
    He, K., Zhang, X., Ren, S., et al.: Deep Residual Learning for Image Recognition. arXiv:1512.03385 (2015)
  8. 8.
    Huang, G., Liu, Z., van der Maaten, L., et al.: Densely Connected Convolutional Networks. arXiv:1608.06993 (2016)
  9. 9.
  10. 10.
    Ioffe, S., Szegedy, C.: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv:1502.03167 (2015)
  11. 11.
    Zhou, B., Khosla, A., Lapedriza, A., et al.: Learning Deep Features for Discriminative Localization. arXiv:1512.04150 (2015)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.University of Information Technology, Vietnam National UniversityHo Chi Minh CityVietnam
  2. 2.Kyanon DigitalHo Chi Minh CityVietnam
  3. 3.Wecheer SAHo Chi Minh CityVietnam
  4. 4.Saigon UniversityHo Chi Minh CityVietnam
  5. 5.Industrial University of Ho Chi Minh CityHo Chi Minh CityVietnam

Personalised recommendations