Optimization of Feature Loss for Image Enhancement
Vishal Burman1, Harshinee Sriram2, S. Usha Kiruthika3

1Vishal Burman*, Bachelor of Technology, Computer Science and Engineering at SRM Institute of Science and Technology, Kattankulathur.
2Harshinee Sriram, Bachelor of Technology, Computer Science and Engineering at SRM Institute of Science and Technology, Kattankulathur.
3S. Usha Kiruthika, Assistant Professor, Department of Computer Science and Engineering in SRM Institute of Science and Technology, Kattankulathur.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 30, 2020. | Manuscript published on April 10, 2020. | PP: 1097-1102 | Volume-9 Issue-6, April 2020. | Retrieval Number: F4203049620/2020©BEIESP | DOI: 10.35940/ijitee.F4203.049620
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-transformation problem is a problem in which an input image is transformed to an output image. In most of the recent methods, a feed-forward neural network is defined which utilizes per-pixel loss between the output image and the ground-truth image. In this paper we have showcased that high quality images can be generated by defining a feature-loss function which is based on high-level perceptual features extracted from pre-trained convolutional networks. We have combined both the approaches that have been formerly mentioned and have proposed a feature-loss function for training a feed-forward neural network capable of image transformation tasks. We have compared out method with that of an optimization based approach, similar to the one utilized in Generative Adversarial Networks (GANs) and our method produced visually appealing results whilst fully capturing the intricate details of the object in the image. 
Keywords: Image Transformation, Super-resolution, Deep Learning, Convolutional Neural Networks
Scope of the Article:  Neural Information Processing