Super-Resolution of Digital Images Using CNN with Leaky ReLU
Jebaveerasingh Jebadurai1, Immanuel Johnraja Jebadurai2, Getzi Jeba Leelipushpam Paulraj3, Nancy Emymal Samuel4
1Jebaveerasingh Jebadurai, Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore (Tamil Nadu), India.
2Immanuel Johnraja Jebadurai, Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore (Tamil Nadu), India.
3Getzi Jeba Leelipushpam Paulraj, Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore (Tamil Nadu), India.
4Nancy Emymal Samuel, System Administrator, Sam Salt Works, Tuticorin, (Tamil Nadu), India.
Manuscript received on 10 October 2019 | Revised Manuscript received on 19 October 2019 | Manuscript Published on 02 November 2019 | PP: 210-212 | Volume-8 Issue-2S11 September 2019 | Retrieval Number: B10340982S1119/2019©BEIESP | DOI: 10.35940/ijrte.B1034.0982S1119
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: Image super-resolution (SR) has been used in many real world applications as a preprocessing phase. The improvement in image resolution increases the performance of image analysis process. The SR of digital images is achieved by taking the low resolution images as inputs. In this article, a novel deeplearning based super-resolution approach is proposed. The proposed approach uses Convolutional Neural Network (CNN) with leaky rectified linear unit (ReLU) for learning and generalization. The experiments with test images taken from USC-SIPI dataset indicate that the proposed approach increases the quality of the images in terms of the quantitative metric peak signal to noise ratio.
Keywords: Super-Resolution, Deep Learning, Convolutional Neural Network, Leaky ReLU.
Scope of the Article: Digital System and Logic Design