APSIPA Transactions on Signal and Information Processing > Vol 10 > Issue 1

Robust deep convolutional neural network against image distortions

Liang-Yao Wang, Institute of Electronics, National Yang Ming Chiao Tung University, Taiwan, Sau-Gee Chen, Institute of Electronics, National Yang Ming Chiao Tung University, Taiwan, Feng-Tsun Chien, Institute of Electronics, National Yang Ming Chiao Tung University, Taiwan, ftchien@mail.nctu.edu.tw
 
Suggested Citation
Liang-Yao Wang, Sau-Gee Chen and Feng-Tsun Chien (2021), "Robust deep convolutional neural network against image distortions", APSIPA Transactions on Signal and Information Processing: Vol. 10: No. 1, e14. http://dx.doi.org/10.1017/ATSIP.2021.14

Publication Date: 11 Oct 2021
© 2021 Liang-Yao Wang, Sau-Gee Chen and Feng-Tsun Chien
 
Subjects
 
Keywords
Convolutional neural networkImage distortionDiscrete cosine transform
 

Share

Open Access

This is published under the terms of the Creative Commons Attribution licence.

Downloaded: 327 times

In this article:
I. INTRODUCTION 
II. RELATED WORK 
III. HYBRID MODULE WITH DCT-DWT-SVD 
IV. EXPERIMENTS AND DATASETS 
V. CONCLUSION 
FINANCIAL SUPPORT 
CONFLICT OF INTEREST 

Abstract

Many approaches have been proposed in the literature to enhance the robustness of Convolutional Neural Network (CNN)-based architectures against image distortions. Attempts to combat various types of distortions can be made by combining multiple expert networks, each trained by a certain type of distorted images, which however lead to a large model with high complexity. In this paper, we propose a CNN-based architecture with a pre-processing unit in which only undistorted data are used for training. The pre-processing unit employs discrete cosine transform (DCT) and discrete wavelets transform (DWT) to remove high-frequency components while capturing prominent high-frequency features in the undistorted data by means of random selection. We further utilize the singular value decomposition (SVD) to extract features before feeding the preprocessed data into the CNN for training. During testing, distorted images directly enter the CNN for classification without having to go through the hybrid module. Five different types of distortions are produced in the SVHN dataset and the CIFAR-10/100 datasets. Experimental results show that the proposed DCT-DWT-SVD module built upon the CNN architecture provides a classifier robust to input image distortions, outperforming the state-of-the-art approaches in terms of accuracy under different types of distortions.

DOI:10.1017/ATSIP.2021.14

Companion

APSIPA Transactions on Signal and Information Processing Deep Neural Networks: Representation, Interpretation, and Applications: Articles Overview
See the other articles that are part of this special issue.