Loading

Learning Based Resolution Enhancement of Digital Images
Jebaveerasingh Jebadurai1, Immanuel Johnraja Jebadurai2, Getzi Jeba Leelipushpam Paulraj3, Nancy Emymal Samuel4
1Jebaveerasingh Jebadurai*, Department of CSE, Karunya Institute of Technology and Sciences, Coimbatore, India. 
2Immanuel Johnraja Jebadurai, Department of CSE, Karunya Institute of Technology and Sciences, Coimbatore, India. 
3Getzi Jeba Leelipushpam Paulraj, Department of CSE, Karunya Institute of Technology and Sciences, Coimbatore, India.  
4Nancy Emymal Samuel, System Administrator, Sam Salt Works, Tuticorin, India.
Manuscript received on August 03, 2019. | Revised Manuscript received on August 28, 2019. | Manuscript published on August 30, 2019. | PP: 3026-3030 | Volume-8 Issue-6, August 2019. | Retrieval Number: F9025088619/2019©BEIESP | DOI: 10.35940/ijeat.F9025.088619
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Image super-resolution (SR), the process that improves the resolution, has been used in many real world applications. SR is the preprocessing phase of majority of these applications. The improvement in image resolution improves the performance of image analysis process. The SR of digital images take the low resolution images as inputs. In this article, a learning based digital image SR approach is proposed. The proposed approach uses Convolutional Neural Network (CNN) with leaky rectified linear unit (ReLU) for learning and generalization. The experiments with the test dataset from USC-SIPI indicate that the proposed approach increases the quality of the images in terms of the quantitative metric peak signal to noise ratio. Further, it avoided the problem of dying ReLU.
Keywords: Convolutional Neural Network, Deep Learning, Leaky ReLU, Super-Resolution.