A Convolution Neural Network Based Classification Approach for Recognizing Traditional Foods of Bangladesh from Food Images

  • Nishat TasnimEmail author
  • Md. Romyull Islam
  • Shaon Bhatta Shuvo
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 940)


The process of identifying food items from an image is one of the promising applications of visual object recognition in computer vision. However, analysis of food items is a particularly challenging task due to the nature of their has achieved by traditional approaches in the field. Deep neural networks have exceeded such solutions. With a goal to successfully applying computer images, which is why a low classification accuracy vision techniques to classify food images based on Inception-v3 model of TensorFlow platform, we use the transfer learning technology to retrain the food category datasets. Our approach shows auspicious results with an average accuracy of 95.2% approximately in correctly recognizing among 7 traditional Bangladeshi foods.


Object recognition Computer vision Deep neural networks Inception-v3 


  1. 1.
  2. 2.
  3. 3.
    Transfer learning. Accessed 3 Sept 2018
  4. 4.
    Islam, M.S., Foysal, F.A., Neehal, N.: InceptB: a CNN Based classification approach for recognizing traditional Bengali games. Procedia Comput. Sci. 143, 592–602 (2018)Google Scholar
  5. 5.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)Google Scholar
  6. 6.
    Convolutional neural network architecture. Accessed 5 Sept 2018
  7. 7.
    The Architecture of Convolutional Neural Network. Accessed 12 Sept 2018
  8. 8.
    Convolutional Neural Network. Accessed 5 Sept 2018
  9. 9.
  10. 10.
    Xia, X., Xu, C., Nan, B.: Inception-v3 for flower classification. In: 2017 2nd International Conference on Image, Vision and Computing (ICIVC), pp. 783–787. IEEE (2017)Google Scholar
  11. 11.
    Mathew, A., Mathew, J., Govind, M., Mooppan, A.: An improved transfer learning approach for intrusion detection. In: 7th International Conference on Advances in Computing and Communications, Cochin, India (2017)Google Scholar
  12. 12.
    Kieffer, B., Babaie, M., Kalra, S., Tizhoosh, H.R.: Convolutional neural networks for histopathology image classification: training vs. using pre-trained networks. In: 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 1–6. IEEE (2017)Google Scholar
  13. 13.
    Xia, X.L., Xu, C., Nan, B.: Facial expression recognition based on tensorflow platform. In: ITM Web of Conferences, vol. 12, p. 01005. EDP Sciences (2017)Google Scholar
  14. 14.
    Batsukh, B.E., Tsend, G.: Effective computer model for recognizing nationality from frontal image (2016)Google Scholar
  15. 15.
    Support vector machine. Accessed 13 Sept 2018
  16. 16.
    Active appearance model. Accessed 15 Sept 2018
  17. 17.
    Cootes, T., Baldock, E.R., Graham, J.: An introduction to active shape models, pp. 223–248 (2000)Google Scholar
  18. 18.
    Backpropagation algorithm. Accessed 11 Sept 2018
  19. 19.
    Cross-entropy. Accessed 8 Sept 2018

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Nishat Tasnim
    • 1
    Email author
  • Md. Romyull Islam
    • 1
  • Shaon Bhatta Shuvo
    • 1
  1. 1.Daffodil International UniversityDhakaBangladesh

Personalised recommendations