Evaluation of Pre-Trained Convolutional Neural Network Models for Object Recognition

  • Authors

    • M Zabir
    • N Fazira
    • Zaidah Ibrahim
    • Nurbaity Sabri
    2018-08-13
    https://doi.org/10.14419/ijet.v7i3.15.17509
  • CNN, AlexNet, GoogLeNet, Caltech101.
  • This paper aims to evaluate the accuracy performance of pre-trained Convolutional Neural Network (CNN) models, namely AlexNet and GoogLeNet accompanied by one custom CNN. AlexNet and GoogLeNet have been proven for their good capabilities as these network models had entered ImageNet Large Scale Visual Recognition Challenge (ILSVRC) and produce relatively good results. The evaluation results in this research are based on the accuracy, loss and time taken of the training and validation processes. The dataset used is Caltech101 by California Institute of Technology (Caltech) that contains 101 object categories. The result reveals that custom CNN architecture produces 91.05% accuracy whereas AlexNet and GoogLeNet achieve similar accuracy which is 99.65%. GoogLeNet consistency arrives at an early training stage and provides minimum error function compared to the other two models.

     

  • References

    1. [1] Shin, H. C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Summers, R. M. (2016). Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning. IEEE Transactions on Medical Imaging, 35(5), 1285–1298.

      [2] Rodrigues, L. F., Naldi, M. C., & Mari, J. F. (2017). HEp-2 Cell Image Classification Based on Convolutional Neural Networks. 2017 Workshop of Computer Vision (WVC), 13–18.

      [3] Hu, W., Huang, Y., Wei, L., Zhang, F., & Li, H. (2015). Deep convolutional neural networks for hyperspectral image classification. Journal of Sensors, pg no

      [4] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D. Rabinovich, A. (2014). Going Deeper with Convolutions. arXiv:1409.4842. http://doi.org/10.1109/CVPR.2015.7298594

      [5] B. Baiping, X. Han, & D. Wu. (2018) Real-Time Crowd Density Estimation Based on Convolutional Neural Networks. 2018 International Conference on Intelligent Transportation, Big Data & Smart City, 691-694

      [6] Subramanian, S. V. (2018). Deep Convolutional For Tiny ImageNet Classification∗, 17319279.

      [7] No, E. (n.d.). A PERFORMANCE ANALYSIS OF CONVOLUTIONAL NEURAL NETWORK MODELS IN SAR TARGET RECOGNITION Naval Aeronautical and Astronautical University , Department of Electronic and Information, (188).

      [8] Vu, M., Francophone, U., &Beurton-aimar, M. (2018). Heritage Image Classification by Convolution Neural Networks, 1–6.

      [9] Gu, S., & Rigazio, L. (2015). Towards Deep Neural Nettwork Architectures, (2013), 1–9.

      [10] Canziani, A., Culurciello, E., & Paszke, A. (2017). Evaluation of neural network architectures for embedded systems. 2017 IEEE International Symposium on Circuits and Systems (ISCAS), 1–4.

      [11] L. Fei-Fei, R. Fergus and P. Perona. (2014). Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. IEEE. CVPR 2004, Workshop on Generative-Model Based Vision.

  • Downloads

  • How to Cite

    Zabir, M., Fazira, N., Ibrahim, Z., & Sabri, N. (2018). Evaluation of Pre-Trained Convolutional Neural Network Models for Object Recognition. International Journal of Engineering & Technology, 7(3.15), 95-98. https://doi.org/10.14419/ijet.v7i3.15.17509