Paper on Facial Manipulation Techniques
C. Malathy1, Mridula Vijendran2, Krishna Maneesha Dendukuri3
1Dr. C. Malathy, SRM Institute of Science & Technology, Chennai (Tamil Nadu), India.
2Mridula Vijendran, SRM Institute of Science & Technology, Chennai (Tamil Nadu), India.
3Krishna Maneesha Dendukuri, SRM Institute of Science &Technology, Chennai (Tamil Nadu), India.
Manuscript received on 21 May 2019 | Revised Manuscript received on 07 June 2019 | Manuscript Published on 15 June 2019 | PP: 302-305 | Volume-8 Issue-1S2 May 2019 | Retrieval Number: A00700581S219/2019©BEIESP
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: Facial manipulation is the manipulation of pose, identity, albedo, expression, and texture for creative, artistic, and aesthetic manipulation in different styles. It’s used in visualizations, videos and image presentations, and digital media, social media, advertising, restoration and preservation of old and damaged photos or images. However, it can also be used for hijacking the facial identity of the target video or image, thus, compromising the integrity of the person in question. This can be accomplished by techniques using supervised convolutional neural networks, unsupervised generative models and physics-based models. These models aim to transfer traits and features that are intuitively comprehensible from the source to the target. Another objective could be to give full control to modify the features in the generated model, in a manner that we can grasp the immediate correlation to the resultant output. This paper considers the various techniques in deep learning and physics simulations to achieve facial manipulation.
Keywords: 3D Parametric Face Models, Neural Style Transfer, Generative Adversarial Networks(GAN), Variational Autoencoders(VAE), Physics-based Facial Manipulation.
Scope of the Article: Foundations of Communication Networks