Training the Image Classifier with and without Data Augmentation

Authors

  • Dr. R. Nithya  Department of Computer Science, Dr. N.G.P. Arts and Science College, Coimbatore, Tamil Nadu, India

DOI:

https://doi.org//10.32628/CSEIT206245

Keywords:

Image Classification, Artificial Neural Networks, Deep Learning, Convolutional Neural Networks, Tensorflow, Data Augmentation

Abstract

The main objective of this paper is to train the image classifier using Convolutional Neural Networks with tensorflow architecture. The proposed paper focus on systematic approaches in classifying the sample set of images using Convolutional Neural Networks. The CNN model with activation function thus classifies the dataset into two categories exactly like human. Thus, the paper highlights the importance of augmentation by comparing their accuracies.

References

  1. A. Krizhevsky, I. Sutskever, and G. E. Hinton.(2012). ImageNet classification with deep convolutional neural networks in Proc. Int. Conf. Neural Inf. Process. Syst., pp. 1097_1105.
  2. Dong, C., Loy, C. C., He, K., & Tang, X. (2016). Image super-resolution using deep Convolutional networks. IEEE transactions on pattern analysis and machine intelligence, 38(2), 295-307.
  3. G. E. Hinton and R. R. Salakhutdinov.( 2006). Reducing the dimensionality of data with neural networks,' Science, vol. 313, no. 5786, pp. 504_507.
  4. Hasbi Ash Shiddieqy, Farkhad Ihsan Hariadi, Trio Adiono. (2017). Implementation of Deep-Learning based Image Classification on Single Board Computer”, International Symposium on Electronics and Smart Devices (ISESD), ISBN 978-1-5386-2779-2, pp. 133-137.
  5. H. Lee, R. Grosse, R. Ranganath, and A. Y. Ng. (2009).Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations,' in Proc. 26th Annu. Int. Conf. Mach. Learn., pp. 609_616.
  6. J. Jebadurai and J. D. Peter. (2018). Deep CS: Deep Convolutional Neural Network and SVM Based Single Image Super-Resolution, Lecture Notes in Computer Science, vol. 11076, pp. 3-13.
  7. J. Nagi et al. (2011).Max-pooling convolutional neural networks for vision based hand gesture recognition, Proc. IEEE Int. Conf. Signal Image Process. Appl. (ICSIPA), pp. 342_347.
  8. K. He, X. Zhang, S. Ren, and J. Sun, (2014).Spatial pyramid pooling in deep convolutional networks for visual recognition, in Proc. Eur. Conf. Comput. Vis., pp. 346–361.
  9. Laila Ma‟rifatul Azizah, Sitti Fadillah Umayah, Slamet Riyadi, Cahya Damarjati, Nafi Ananda Utama . (2017). Deep Learning Implementation using Convolutional Neural Network in Mangosteen Surface Defect Detection, ICCSCE, ISBN 978-1-5386-3898-9, pp. 242-246.
  10. Min-Chun Yang Yu-Chiang Frank Wang. (2013). A Self-Learning Approach to Single Image Super-Resolution, IEEE Trans. Multimedia, vol. 15, no. 3, pp. 498–508.
  11. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. (2014). Dropout: A simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929_1958.
  12. Rika Sustika, Asri R. Yuliani, Efendi Zaenudin, Hilman F. Pardede . (2017). On Comparison of Deep Learning Architectures for Distant Speech Recognition, 2nd International Conferences on Information Technology, Information Systems and Electrical Engineering (ICITISEE), ISBN 978-1-5386-0659-9, pp. 17-21.
  13. Rui Wang, Wei Li, Runnan Qin and JinZhong Wu. (2017). Blur Image Classification based on Deep Learning, IEEE, ISBN 978-1-5386-1621-5 pp. 1-6.
  14. Sachchidanand Singh, Nirmala Singh. (2017). Object Classification to Analyze Medical Imaging Data using Deep Learning, International Conference on Innovations in information Embedded and Communication Systems (ICIIECS), ISBN 978-1-5090-3295-2, pp. 1-4.
  15. Sameer Khan and Suet-Peng Yong, (2017). A Deep Learning Architecture for Classifying Medical Image of Anatomy Object, Annual Summit and Conference, ISBN 978-1-5386-1543-0, pp. 1661-1668.
  16. Sebastian Stabinger, Antonio Rodr´ıguez-S´anchez. (2017). Evaluation of Deep Learning on an Abstract Image Classification Dataset, IEEE International Conference on Computer Vision Workshops (ICCVW), ISBN 978-1-5386-1035-0, pp. 2767-2772.
  17. S. Ioffe and C. Szegedy. (2015).Batch normalization: Accelerating deep network training by reducing internal covariate shift, in Proc. Int. Conf. Mach. Learn., 2015, pp. 448_456.
  18. Teny Handhayani, Janson Hendryli, Lely Hiryantyo, (2017). Comparison of Shallow and Deep Learning Models for Classification of Lasem Batik Patterns, ICICoS, ISBN 978-1-5386-0904-0, pp. 11-16.
  19. Ye Tao, Ming Zhang, Mark Parsons. (2017). Deep Learning in Photovoltaic Penetration Classification, IEEE Power & Energy Society General Meeting, ISBN 978-1-5386-2213-1, pp. 1-5.
  20. W. Ouyang et al. (2014). Deep ID-Net: Multi-stage and deformable deep convolutional neural networks for object detection.Online]. Available: https://arxiv.org/abs/1409.3505.

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2020-04-30

Issue

Volume 6, Issue 2, March-April-2020

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Dr. R. Nithya, " Training the Image Classifier with and without Data Augmentation, IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 6, Issue 2, pp.172-178, March-April-2020. Available at doi : https://doi.org/10.32628/CSEIT206245