Scene Classification Using Transfer Learning

  • Nikhil Damodaran
  • V. SowmyaEmail author
  • D. Govind
  • K. P. Soman
Part of the Studies in Computational Intelligence book series (SCI, volume 804)


Categorization of scene images is considered as a challenging prospect due to the fact that different classes of scene images often share similar image statistics. This chapter presents a transfer learning based approach for scene classification. A pre-trained Convolutional Neural Network (CNN) is used as a feature extractor for the images. The pre-trained network along with classifiers such as Support Vector Machines (SVM) or Multi Layer Perceptron (MLP) are used to classify the images. Also, the effect of single plane images such as, RGB2Gray, SVD Decolorized and Modified SVD decolorized images are analysed based on classification accuracy, class-wise precision, recall, F1-score and equal error rate (EER). The classification experiment for SVM was also done using a dimensionality reduction technique known as principal component analysis (PCA) on the feature vector. By comparing the results of models trained on RGB images with those grayscale images, the difference in the results is very small. These grayscale images were capable of retaining the required shape and texture information from the original RGB images and were also sufficient to categorize the classes of the given scene images.


  1. 1.
    Rasiwasia, N., Vasconcelos, N.: Scene classification with low-dimensional semantic spaces and weak supervision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–6 (2008)Google Scholar
  2. 2.
    Viitaniemi, V., Laaksonen, J.: Techniques for still image scene classification and object detection. In: International Conference on Artificial Neural Networks, pp. 35–44 (2006)CrossRefGoogle Scholar
  3. 3.
    Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2(1), 1–127 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)CrossRefGoogle Scholar
  5. 5.
    Razavian, A.s., Hossein, A., Josephine, S., Stefan, C.: CNN features off-the-shelf: an astounding baseline for recognition. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 512–519 (2014)Google Scholar
  6. 6.
    Oquab, M., Leon, B., Iva, L., Josef, S.: Learning and transferring mid-level image representations using convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1717–1724 (2014)Google Scholar
  7. 7.
    Jeff, D., Yangqing, J., Vinyals, O., Judy, H., Zhang, N., Eric, T., Trevor, D.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: International Conference on Machine Learning, pp. 647–655 (2014)Google Scholar
  8. 8.
    Sachin, R., Sowmya, V., Govind, D., Soman, K.P.: Dependency of various color and intensity planes on CNN based image classification. In: International Symposium on Signal Processing and Intelligent Recognition Systems, pp. 167–177 (2017)Google Scholar
  9. 9.
    Aude, O., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. Comput. Vis. 42(3), 145–175 (2001)CrossRefzbMATHGoogle Scholar
  10. 10.
    Liang, Z., Yali, Z., Shengjin, W., Jingdong, W., Tian, Q.: Good practice in CNN feature transfer (2016). arXiv:1604.00133
  11. 11.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  12. 12.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv:1409.1556
  13. 13.
    Jolliffe, I., Cadima, J.: Principal component analysis: a review and recent developments. Philos. Trans. Ser. A Math. Phys. Eng. Sci. 374(2065), 1–10 (2016)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Sowmya, V., Govind, D., Soman, K.: Significance of incorporating chrominance information for effective color-to-grayscale image conversion. Signal Image Video Process. 11(1), 129–136 (2017)CrossRefGoogle Scholar
  15. 15.
    Kede, M., Tiesong, Z., Kai, Z., Zhou, W.: Objective quality assessment for color-to-gray image conversion. IEEE Trans. Image Process. 24(12), 4673–4685 (2015)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Viswanathan, S., Divakaran, G., Soman, K.P.: Significance of perceptually relevant image decolorization for scene classification. J. Electron. Imaging 26(6), 063019 (2017)CrossRefGoogle Scholar
  17. 17.
    Zhou, B., Khosla, A., Lapedriza, A., Torralba, A., Oliva, A.: Places: an image database for deep scene understanding (2016). arXiv:1610.02055
  18. 18.
    Kaiming, H., Xiangyu, Z., Shaoqing, R., Jian, S.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)CrossRefGoogle Scholar
  19. 19.
    Ross, G., Jeff, D., Trevor, D., Jitendra, M.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)Google Scholar
  20. 20.
    Razavian, A.S., Sullivan, J., Carlsson, S., Maki, A.: Visual instance retrieval with deep convolutional networks. ITE Trans. Media Technol. Appl. 4(3), 251–258 (2016)CrossRefGoogle Scholar
  21. 21.
    Ali, S., Josephine, S., Stefan, C., Atsuto, M.: CNN features off-the-shelf: an astounding baseline for recognition. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 806–813 (2014)Google Scholar
  22. 22.
    Artem, B., Anton, S., Alexandr, C., Victor, L.: Neural codes for image retrieval. In: European Conference on Computer Vision, pp. 584–599. Springer (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Nikhil Damodaran
    • 1
  • V. Sowmya
    • 1
    Email author
  • D. Govind
    • 1
  • K. P. Soman
    • 1
  1. 1.Center for Computational Engineering and Networking (CEN)Amrita School of Engineering, Amrita Vishwa VidyapeethamCoimbatoreIndia

Personalised recommendations