Next Article in Journal
Research on Angle and Stiffness Cooperative Tracking Control of VSJ of Space Manipulator Based on LESO and NSFAR Control
Previous Article in Journal
Comprehensive Study on Dynamic Parameters of Symmetric and Asymmetric Ultracapacitors
Open AccessArticle

Multi-Scale Inception Based Super-Resolution Using Deep Learning Approach

Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, Thailand
*
Author to whom correspondence should be addressed.
Electronics 2019, 8(8), 892; https://doi.org/10.3390/electronics8080892
Received: 26 June 2019 / Revised: 5 August 2019 / Accepted: 6 August 2019 / Published: 13 August 2019
(This article belongs to the Section Circuit and Signal Processing)
  |  
PDF [10327 KB, uploaded 13 August 2019]
  |  

Abstract

Single image super-resolution (SISR) aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) image. In order to address the SISR problem, recently, deep convolutional neural networks (CNNs) have achieved remarkable progress in terms of accuracy and efficiency. In this paper, an innovative technique, namely a multi-scale inception-based super-resolution (SR) using deep learning approach, or MSISRD, was proposed for fast and accurate reconstruction of SISR. The proposed network employs the deconvolution layer to upsample the LR image to the desired HR image. The proposed method is in contrast to existing approaches that use the interpolation techniques to upscale the LR image. Primarily, interpolation techniques are not designed for this purpose, which results in the creation of undesired noise in the model. Moreover, the existing methods mainly focus on the shallow network or stacking multiple layers in the model with the aim of creating a deeper network architecture. The technique based on the aforementioned design creates the vanishing gradients problem during the training and increases the computational cost of the model. Our proposed method does not use any hand-designed pre-processing steps, such as the bicubic interpolation technique. Furthermore, an asymmetric convolution block is employed to reduce the number of parameters, in addition to the inception block adopted from GoogLeNet, to reconstruct the multiscale information. Experimental results demonstrate that the proposed model exhibits an enhanced performance compared to twelve state-of-the-art methods in terms of the average peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) with a reduced number of parameters for the scale factor of 2 × , 4 × , and 8 × . View Full-Text
Keywords: deep learning; multi-scale information; asymmetric convolution; residual skip connection; inception module deep learning; multi-scale information; asymmetric convolution; residual skip connection; inception module
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Muhammad, W.; Aramvith, S. Multi-Scale Inception Based Super-Resolution Using Deep Learning Approach. Electronics 2019, 8, 892.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Electronics EISSN 2079-9292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top