New Access to Improve Super Resolution using Convolution Neural Network
Rahul Bhattacharya1, K. Parvathi2
1Rahul Bhattacharya, Department of Electronics and Tele Communication, KIIT University, Bhubaneswar (Odisha), India.
2K.Parvathi, Department of Electronics and Tele Communication, KIIT University, Bhubaneswar (Odisha), India.
Manuscript received on 15 August 2019 | Revised Manuscript received on 27 August 2019 | Manuscript Published on 06 September 2019 | PP: 160-165 | Volume-8 Issue- 6S, August 2019 | Retrieval Number: F10330886S19/19©BEIESP | DOI: 10.35940/ijeat.F1033.0886S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Super Resolution is the process to enhance image quality by increasing the pixel densities from a low resolution image. Several methods are proposed in the last few decades. We survey several methods like filtration method i.e. Scalar Smoothness Index filtration, learning based method using Convolution Neural Network. We also propose a new algorithm where we use filtration technique as a preprocessing technique of learning based method.
Keywords: Wavelet Decomposition Technique, SSI(Scalar Smoothness Index), SRCNN (Super-Resolution Convolution Neural Network), PSNR (Peak_Signal-to-Noise_Ratio).
Scope of the Article: Neural Information Processing