A Study on CNN Transfer Learning for Image Classification

  • Mahbub Hussain
  • Jordan J. Bird
  • Diego R. FariaEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 840)


Many image classification models have been introduced to help tackle the foremost issue of recognition accuracy. Image classification is one of the core problems in Computer Vision field with a large variety of practical applications. Examples include: object recognition for robotic manipulation, pedestrian or obstacle detection for autonomous vehicles, among others. A lot of attention has been associated with Machine Learning, specifically neural networks such as the Convolutional Neural Network (CNN) winning image classification competitions. This work proposes the study and investigation of such a CNN architecture model (i.e. Inception-v3) to establish whether it would work best in terms of accuracy and efficiency with new image datasets via Transfer Learning. The retrained model is evaluated, and the results are compared to some state-of-the-art approaches.


  1. 1.
    TensorFlow: Image Recognition (2018). Accessed 20 Apr 2018
  2. 2.
    Christian Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovih, R.: Going Deeper with Convolutions ( (2015)Google Scholar
  3. 3.
    Lin, M., Chen, Q., Yan, S.: Network in Network. ICLR submission ( (2013)Google Scholar
  4. 4.
    Nguyen, N.: Computational Collective Intelligence. Springer, Cham (2016)Google Scholar
  5. 5.
    Arun, P., Katiyar, S.: A CNN based Hybrid approach towards automatic age registration. Geodesy Cartography 62(1), 33–49 (2013)CrossRefGoogle Scholar
  6. 6.
    Rohrer, B.: How do Convolutional Neural Networks work? (2016). Accessed 20 Apr 2018
  7. 7.
    ImageNet: About (2016). Accessed 20 Apr 2018
  8. 8.
    Gao, Y., Mosalam, K.: Deep transfer learning for image-based structural damage recognition. Comput. Aided Civ. Infrastruct. Eng. (2018)Google Scholar
  9. 9.
    Larsen-Freeman, D.: Transfer of learning transformed. Lang. Learn. 63, 107–129 (2013)CrossRefGoogle Scholar
  10. 10.
    Krizhevsky, A.: The CIFAR-10 dataset (2009). Accessed 20 Apr 2018
  11. 11.
    Vision Caltech: Computational Vision (2018). Accessed 20 Apr 2018
  12. 12.
    Wu, J.: CNN for Dummies. Nanjing University (2015)Google Scholar
  13. 13.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: IEEE CVPR 2016: Computer Vision and Pattern Recognition (2016)Google Scholar
  14. 14. Convolutional Neural Network (2018). Accessed 20 Apr 2018

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Mahbub Hussain
    • 1
  • Jordan J. Bird
    • 1
  • Diego R. Faria
    • 1
    Email author
  1. 1.School of Engineering and Applied ScienceAston UniversityBirminghamUK

Personalised recommendations