Browse > Article
http://dx.doi.org/10.7472/jksii.2021.22.1.23

A Noise-Tolerant Hierarchical Image Classification System based on Autoencoder Models  

Lee, Jong-kwan (Department of Computer Science, Korea Military Academy)
Publication Information
Journal of Internet Computing and Services / v.22, no.1, 2021 , pp. 23-30 More about this Journal
Abstract
This paper proposes a noise-tolerant image classification system using multiple autoencoders. The development of deep learning technology has dramatically improved the performance of image classifiers. However, if the images are contaminated by noise, the performance degrades rapidly. Noise added to the image is inevitably generated in the process of obtaining and transmitting the image. Therefore, in order to use the classifier in a real environment, we have to deal with the noise. On the other hand, the autoencoder is an artificial neural network model that is trained to have similar input and output values. If the input data is similar to the training data, the error between the input data and output data of the autoencoder will be small. However, if the input data is not similar to the training data, the error will be large. The proposed system uses the relationship between the input data and the output data of the autoencoder, and it has two phases to classify the images. In the first phase, the classes with the highest likelihood of classification are selected and subject to the procedure again in the second phase. For the performance analysis of the proposed system, classification accuracy was tested on a Gaussian noise-contaminated MNIST dataset. As a result of the experiment, it was confirmed that the proposed system in the noisy environment has higher accuracy than the CNN-based classification technique.
Keywords
Image classification; Deep learning; Machine learning; Autoencoder; Noise;
Citations & Related Records
연도 인용수 순위
  • Reference
1 G. Huang, et al. "Densely connected convolutional networks," Proceedings of the IEEE conference on computer vision and pattern recognition, 2017. https://doi.org/10.1109/cvpr.2017.243   DOI
2 A. G. HOWARD, et al. "Mobilenets: Efficient convolutional neural networks for mobile vision applications," arXiv preprint arXiv:1704.04861, 2017. https://arxiv.org/abs/1704.04861
3 J. Hu, Li Shen, and Gang Sun, "Squeeze-and-excitation networks," Proceedings of the IEEE conference on computer vision and pattern recognition, 2018. https://doi.org/10.1109/cvpr.2018.00745   DOI
4 B. Zoph, "Learning transferable architectures for scalable image recognition," Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. https://doi.org/10.1109/cvpr.2018.00907   DOI
5 Goodfellow, Ian, Yoshua Bengio, and Aaron Courville, "Deep learning," MIT press, 2016. https://www.deeplearningbook.org
6 Simonyan, K., & Zisserman, A., "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014. https://arxiv.org/abs/1409.1556
7 Cisse, Moustapha M., et al. "Houdini: Fooling deep structured visual and speech recognition models with adversarial examples," Advances in neural information processing systems, 2017. https://papers.nips.cc/paper/7273-houdini-fooling-deep-structured-visual-and-speech-recognition-models-with-adversarial-examples.pdf
8 H. Kwon, Y. Kim, H. Yoon and D. Choi, "Selective Audio Adversarial Example in Evasion Attack on Speech Recognition System," IEEE Transactions on Information Forensics and Security, vol. 15, pp. 526-538, 2020. https://doi.org/10.1109/tifs.2019.2925452   DOI
9 R. H. Chan, Chung-Wa Ho and M. Nikolova, "Saltand-pepper noise removal by median-type noise detectors and detail-preserving regularization," IEEE Transactions on Image Processing, Vol. 14, No. 10, pp. 1479-1485, 2005. https://doi.org/10.1109/tip.2005.852196   DOI
10 Roy, S. S., Hossain, S. I., Akhand, M. A. H., & Murase, K. "A robust system for noisy image classification combining denoising autoencoder and convolutional neural network," International Journal of Advanced Computer Science and Applications, Vol. 9, No. 4, pp. 224-235, 2018. https://doi.org/10.14569/ijacsa.2018.090131   DOI
11 Krizhevsky, A., Sutskever, I., & Hinton, G. E. "Imagenet classification with deep convolutional neural networks," Commun. ACM, Vol. 60, No. 6, pp. 84-90, 2017. https://doi.org/10.1145/3065386   DOI
12 Sun, Lu, Mingtian Tan, and Zhe Zhou. "A survey of practical adversarial example attacks," Cybersecurity, 2018. https://doi.org/10.1186/s42400-018-0012-9   DOI
13 Charte, David, et al. "A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines," Information Fusion Vol 44, pp. 78-96, 2018. https://doi.org/10.1016/j.inffus.2017.12.007   DOI
14 K. He, et al. "Deep residual learning for image recognition," Proceedings of the IEEE conference on computer vision and pattern recognition, 2016. https://doi.org/10.1109/cvpr.2016.90   DOI
15 Wu, Jianxin. "Introduction to convolutional neural networks," National Key Lab for Novel Software Technology, Nanjing University, 2020. https://cs.nju.edu.cn/wujx/teaching/15_CNN.pdf
16 Kuo, C-C. Jay. "Understanding convolutional neural networks with a mathematical model," Journal of Visual Communication and Image Representation, Vol. 41, pp. 406-413, 2016. https://doi.org/10.1016/j.jvcir.2016.11.003   DOI
17 C. Szegedy, et al. "Going deeper with convolutions," Proceedings of the IEEE conference on computer vision and pattern recognition, 2015. https://doi.org/10.1109/cvpr.2015.7298594   DOI