Semantic Image to Image Translation using Machine Learning Algorithms
G.Pranavi1, M.Pranava Brunda2, P.Jashwanth3, V.Naga Chaitanya4, D.Rajeswara Rao5
1G.Pranavi*, Department of CSE, VR Siddhartha Engineering College, Vijayawada, India.
2M.Pranava Brunda, Department of CSE, VR Siddhartha Engineering College, Vijayawada, India.
3P.Jashwanth, Department of CSE, VR Siddhartha Engineering College, Vijayawada, India.
4V.Naga Chaitanya, Department of CSE, VR Siddhartha Engineering College, Vijayawada, India.
5D.Rajeswara Rao, Department of CSE, VR Siddhartha Engineering College, Vijayawada, India.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 27, 2020. | Manuscript published on April 10, 2020. | PP: 1973-1976 | Volume-9 Issue-6, April 2020. | Retrieval Number: F4712049620/2020©BEIESP | DOI: 10.35940/ijitee.F4712.049620
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: In semantic image-to-image translation, the goal will be to learn mapping between an input image and the output image. A model of semantic image to image translation problem using Cycle GAN algorithm is proposed. Given a set of paired or unpaired images a transformation is learned to translate the input image into the specified domain. The dataset considered is cityscape dataset. In the cityscape dataset, the semantic images are converted into photographic images. Here a Generative Adversarial Network algorithm called Cycle GAN algorithm with cycle consistency loss is used. The cycle GAN algorithm can be used to transform the semantic image into a photographic or real image. The cycle consistency loss compares the real image and the output image of the second generator and gives the loss functions. In this paper, the model shows that by considering more training time we get the accurate results and the image quality will be improved. The model can be used when images from one domain needs to be converted into another domain inorder to obtain high quality of images.
Keywords: Cycle GAN, Cycle Consistency loss, Semantic, Translation
Scope of the Article: Semantic web