Open AccessHuman Face Generation using Deep Convolution Generative Adversarial Network
Author(s) -
Ankita Kesari Naman and Sudha Narang Chaudhary Sarimurrab
Publication year - 2021
Publication title -
international journal of modern trends in science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-3778
DOI - 10.46501/ijmtst070127
Subject(s) - generative grammar , computer science , adversarial system , deep learning , artificial intelligence , face (sociological concept) , field (mathematics) , convolution (computer science) , machine learning , generative adversarial network , artificial neural network , mathematics , social science , sociology , pure mathematics
The Generative Models have gained considerable attention in the field of unsupervised learning via a newand practical framework called Generative Adversarial Networks (GAN) due to its outstanding datageneration capability. Many models of GAN have proposed, and several practical applications emerged invarious domains of computer vision and machine learning. Despite GAN's excellent success, there are stillobstacles to stable training. In this model, we aim to generate human faces through un-labelled data via thehelp of Deep Convolutional Generative Adversarial Networks. The applications for generating faces are vastin the field of image processing, entertainment, and other such industries. Our resulting model is successfullyable to generate human faces from the given un-labelled data and random noise.