Advertisement

An Efficient Deep Convolutional Neural Network for Visual Image Classification

  • Basma Abd El-Rahiem
  • Muhammad Atta Othman AhmedEmail author
  • Omar Reyad
  • Hani Abd El-Rahaman
  • Mohamed Amin
  • Fathi Abd El-Samie
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 921)

Abstract

Such a hot open issue in the area of computer vision is the classification of visual images especially in Internet of Things (IoT) and remote mid-band and high-band based connections. In this paper, we propose a robust and efficient taxonomy framework. The proposed model utilizes the well-known convolutional neural network composites to construct a robust Visual Image Classification Network (VICNet). The VICNet consists of three convolutional layers, four Relu/Leaky Relu activation layers, three max-pooling layers and only two fully connected layers for extracting expected input image features. To make the training process faster, we used non-saturating neurons with a very efficient Graphics Processing Unit (GPU) implementation for the convolution operation. To minimize over-fitting issue in the fully-connected layers, we utilized a recently-developed regularization approach “dropout” with a dropping probability of 50%. The proposed VICNet framework has a high potential capability in the recognition of test images. The experimental and simulations results proven the efficacy of the proposed model.

Keywords

Deep learning Visual image classification Convolutional neural network Deep feature extraction Transfer learning 

References

  1. 1.
    Lee, J.-G., Jun, S., Cho, Y.-W., Lee, H., Kim, G.B., Seo, J.B., Kim, N.: Deep learning in medical imaging general overview. Korean J. Radiol. 18(4), 570–584 (2017)CrossRefGoogle Scholar
  2. 2.
    Ahmed, M.A.O., Didaci, L., Lavi, B., Fumera, G.: Using diversity for classifier ensemble pruning: an empirical investigation. Theor. Appl. Inform. 29(1&2), 25–39 (2018)CrossRefGoogle Scholar
  3. 3.
    Cai, J., Luo, J., Wang, S., Yang, S.: Feature selection in machine learning: a new perspective. Neurocomputing 300, 70–79 (2018)CrossRefGoogle Scholar
  4. 4.
    Zhang, T., El-Latif, A.A.A., Wang, N., Li, Q., Niu, X.: A new image segmentation method via fusing NCut eigenvectors maps. In: Proceedings of SPIE 8334, Fourth International Conference on Digital Image Processing (ICDIP 2012), p. 833430 (2012)Google Scholar
  5. 5.
    Bai, X., Zhang, T., Wang, C., El-Latif, A.A.A., Niu, X.: A fully automatic player detection method based on one-class SVM. IEICE Trans. Inf. Syst. 96(2), 387–391 (2013)CrossRefGoogle Scholar
  6. 6.
    Shi, Z., Yu, L., El-Latif, A.A.A., Niu, X.: Skeleton modulated topological perception map for rapid viewpoint selection. IEICE Trans. Inf. Syst. 95(10), 2585–2588 (2012)CrossRefGoogle Scholar
  7. 7.
    Khfagy, M., AbdelSatar, Y., Reyad, O., Omran, N.: An integrated smoothing method for fingerprint recognition enhancement. In: International Conference on Advanced Intelligent Systems and Informatics, pp. 407–416. Springer, Cham (2016)Google Scholar
  8. 8.
    Ahmed, M.A.O., Reyad, O., AbdelSatar, Y., Omran, N.F.: Multi-filter score-level fusion for fingerprint verification. In: International Conference on Advanced Machine Learning Technologies and Applications, pp. 624–633. Springer, Cham (2018)Google Scholar
  9. 9.
    El-Sayed, M.A., Khafagy, M.A.: An identification system using eye detection based on wavelets and neural networks. arXiv preprint arXiv:1401.5108 (2014)
  10. 10.
    Nife, F., Kotulski, Z., Reyad, O.: New SDN-oriented distributed network security system. Appl. Math. Inf. Sci. 12(4), 673–683 (2018)CrossRefGoogle Scholar
  11. 11.
    Gad, R., Talha, M., El-Latif, A.A.A., Zorkany, M., El-Sayed, A., El-Fishawy, N., Muhammad, G.: Iris recognition using multi-algorithmic approaches for cognitive internet of things (CIoT) framework. Future Gener. Comput. Syst. 89, 178–191 (2018)CrossRefGoogle Scholar
  12. 12.
    Peng, J., El-Latif, A.A.A., Belazi, A., Kotulski, Z.: Efficient chaotic nonlinear component for secure cryptosystems. In: Ninth International Conference on Ubiquitous and Future Networks (ICUFN), pp. 989–993. IEEE (2017)Google Scholar
  13. 13.
    Shiddieqy, H.A., Hariadi, F.I., Adiono, T.: Implementation of deep-learning based image classification on single board computer. In: 2017 International Symposium on Electronics and Smart Devices (ISESD), pp. 133–137. IEEE (2017)Google Scholar
  14. 14.
    Liu, R., Yang, B., Zio, E., Chen, X.: Artificial intelligence for fault diagnosis of rotating machinery: a review. Mech. Syst. Sig. Process. 108, 33–47 (2018)CrossRefGoogle Scholar
  15. 15.
    Gibson, E., Li, W., Sudre, C., Fidon, L., Shakir, D.I., Wang, G., Rosen, Z.E., Gray, R., Doel, T., Hu, Y., Whyntie, T., Nachevc, P., Modat, M., Barratta, D.C., Ourselin, S., Cardoso, M.J., Vercauteren, T.: NiftyNet: a deep-learning platform for medical imaging. Comput. Methods Programs Biomed. 158, 113–122 (2018)CrossRefGoogle Scholar
  16. 16.
    Hu, W., Huang, Y., Wei, L., Zhang, F., Li, H.: Deep convolutional neural networks for hyperspectral image classification. J. Sens. 2015, 12 (2015)CrossRefGoogle Scholar
  17. 17.
    El-Sayed, M.A., Estaitia, Y.A., Khafagy, M.A.: Automated edge detection using convolutional neural network. Int. J. Adv. Comput. Sci. Appl. 4(10), 10–20 (2013)Google Scholar
  18. 18.
    Lavi, B., Ahmed, M.A.O.: Interactive fuzzy cellular automata for fast person re-identification. In: The International Conference on Advanced Machine Learning Technologies and Applications (AMLTA2018), pp. 147–157. Springer, Cham (2018)Google Scholar
  19. 19.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)CrossRefGoogle Scholar
  20. 20.
    Li, J., Zhang, B., Lu, G., Zhang, D.: Generative multi-view and multi-feature learning for classification. Inf. Fusion 45, 215–226 (2019)CrossRefGoogle Scholar
  21. 21.
    Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Ahmed, M.A.O.: Trained neural networks ensembles weight connections analysis. In: International Conference on Advanced Machine Learning Technologies and Applications, pp. 242–251. Springer, Cham (2018)Google Scholar
  23. 23.
    Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, pp. 1–9, (2015). IEEEGoogle Scholar
  24. 24.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, California, USA, pp. 1097–105 (2012)Google Scholar
  25. 25.
    He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 770–778, (2016)Google Scholar
  26. 26.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2015, 2017). https://arxiv.org/pdf/1409.1556v6.pdf
  27. 27.
    Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.-F.: Stanford dogs dataset (2011). http://vision.stanford.edu/aditya86/ImageNetDogs
  28. 28.
    Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.-F.: Novel dataset for fine-grained image categorization. In: First Workshop on Fine-Grained Visual Categorization, IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, June 2011Google Scholar
  29. 29.
    MATLAB: Statistics and Machine Learning Toolbox. The mathworks (2018)Google Scholar
  30. 30.
    Sokolova, M., Lapalme, G.: A systematic analysis of performance measures for classification tasks. Inf. Process. Manag. 45(4), 427–437 (2009)CrossRefGoogle Scholar
  31. 31.
    Khfagy, M.A.O.A.: Visual image classification convolutional network (VICNET) (2019). https://github.com/mkhfagy/VICNet

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Faculty of ScienceMenoufia UniversityShibin El KomEgypt
  2. 2.Faculty of Computers and InformationSouth Valley UniversityLuxorEgypt
  3. 3.Faculty of ScienceSohag UniversitySohagEgypt
  4. 4.Faculty of Electronic EngineeringMenoufia UniversityShibin El KomEgypt

Personalised recommendations