Dual Autoencoder Network with Separable Convolutional Layers for Denoising and Deblurring Images
Open Access
- 13 September 2022
- journal article
- research article
- Published by MDPI AG in Journal of Imaging
- Vol. 8 (9) , 250
Abstract
A dual autoencoder employing separable convolutional layers for image denoising and deblurring is represented. Combining two autoencoders is presented to gain higher accuracy and simultaneously reduce the complexity of neural network parameters by using separable convolutional layers. In the proposed structure of the dual autoencoder, the first autoencoder aims to denoise the image, while the second one aims to enhance the quality of the denoised image. The research includes Gaussian noise (Gaussian blur), Poisson noise, speckle noise, and random impulse noise. The advantages of the proposed neural network are the number reduction in the trainable parameters and the increase in the similarity between the denoised or deblurred image and the original one. The similarity is increased by decreasing the main square error and increasing the structural similarity index. The advantages of a dual autoencoder network with separable convolutional layers are demonstrated by a comparison of the proposed network with a convolutional autoencoder and dual convolutional autoencoder.Keywords
This publication has 70 references indexed in Scilit:
- An adaptive decision based kriging interpolation algorithm for the removal of high density salt and pepper noise in imagesComputers and Electrical Engineering, 2018
- Jaya based functional link multilayer perceptron adaptive filter for Poisson noise suppression from X-ray imagesMultimedia Tools and Applications, 2018
- Spatially adaptive denoising for X-ray cardiovascular angiogram imagesBiomedical Signal Processing and Control, 2018
- Combination of Spatial Domain Filters for Speckle Noise Reduction in Ultrasound Medical ImagesAdvances in Electrical and Electronic Engineering, 2018
- A Robust System for Noisy Image Classification Combining Denoising Autoencoder and Convolutional Neural NetworkInternational Journal of Advanced Computer Science and Applications, 2018
- Types of recurrent neural networks for non-linear dynamic system modelling2017
- Cellular neural network as a non-linear filter of impulse noise2017
- A split signal polynomial as a model of an impulse noise filter for speech signal recoveryJournal of Physics: Conference Series, 2017
- Operator approach to nonlinear compensator synthesys for communication systems2016
- Synthesis of neural pulse interference filters for image restorationRadioelectronics and Communications Systems, 2008