• Journal of Internet Computing and Services
    ISSN 2287 - 1136(Online) / ISSN 1598 - 0170 (Print)
    http://jics.or.kr/

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


Jong-kwan Lee, Journal of Internet Computing and Services, Vol. 22, No. 1, pp. 23-30, Feb. 2021
10.7472/jksii.2021.22.1.23, Full Text:
Keywords: Image Classification, Deep Learning, Machine Learning, Autoencoder, noise

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.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[APA Style]
Jong-kwan Lee (2021). A Noise-Tolerant Hierarchical Image Classification System based on Autoencoder Models. Journal of Internet Computing and Services, 22(1), 23-30. DOI: 10.7472/jksii.2021.22.1.23.

[IEEE Style]
J. Lee, "A Noise-Tolerant Hierarchical Image Classification System based on Autoencoder Models," Journal of Internet Computing and Services, vol. 22, no. 1, pp. 23-30, 2021. DOI: 10.7472/jksii.2021.22.1.23.

[ACM Style]
Jong-kwan Lee. 2021. A Noise-Tolerant Hierarchical Image Classification System based on Autoencoder Models. Journal of Internet Computing and Services, 22, 1, (2021), 23-30. DOI: 10.7472/jksii.2021.22.1.23.