This paper is published in Volume-6, Issue-6, 2020
Area
Artificial Intelligence
Author
Yasoda Krishna Reddy Annapureddy, Gangadhar Katuri, Uma Eswar Dande, Hussain Shaik
Org/Univ
K L University, Guntur, Andhra Pradesh, India
Pub. Date
12 December, 2020
Paper ID
V6I6-1207
Publisher
Keywords
Fake Face, Generative Adversarial Network, GAN

Citationsacebook

IEEE
Yasoda Krishna Reddy Annapureddy, Gangadhar Katuri, Uma Eswar Dande, Hussain Shaik. Fake face creation using generative adversarial network, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Yasoda Krishna Reddy Annapureddy, Gangadhar Katuri, Uma Eswar Dande, Hussain Shaik (2020). Fake face creation using generative adversarial network. International Journal of Advance Research, Ideas and Innovations in Technology, 6(6) www.IJARIIT.com.

MLA
Yasoda Krishna Reddy Annapureddy, Gangadhar Katuri, Uma Eswar Dande, Hussain Shaik. "Fake face creation using generative adversarial network." International Journal of Advance Research, Ideas and Innovations in Technology 6.6 (2020). www.IJARIIT.com.

Abstract

Presently Nowadays numerous organizations are putting their cash for ads primarily in type of boards. For announcements numerous organizations are putting cash in models. To limit we can make the phony face utilizing Artificial Intelligence. The Generative Adversarial Network (GAN) yields bleeding edge achieves data driven certifiable generative picture illustrating. GANs can be utilized to create a photograph practical picture from a low measurement arbitrary noise. We reveal and examine its brand name antiquated rarities, propose some switches in both model planning and preparing procedures to address them. Specifically, we update the generator standardization, and regularize generator to connect with unfathomable adornment in the orchestrating from slow codes to pictures. This makes it conceivable to dependably ascribe a made picture to a specific affiliation. We other than envision how well the generator uses its yield objective, and recognize a breaking point issue, prodding us to plan greater models for additional quality improvements. When all is said in done, our improved model renames the top tier in unequivocal picture showing, both with respect to existing course quality estimations similarly as observed picture quality.
Paper PDF