Welcome to the InfoSci Platform
Modified GAN for Natural Occlusion Detection and Inpainting of Raw Footage From Video Surveillance

Modified GAN for Natural Occlusion Detection and Inpainting of Raw Footage From Video Surveillance

Pritham Sriram G., Prasana Venkatesh S., Deepak Raj P., Angelin Gladston
Copyright: © 2022 |Volume: 3 |Issue: 1 |Pages: 18
ISSN: 2644-1675|EISSN: 2644-1683|EISBN13: 9781683183938|DOI: 10.4018/IJBDIA.312852
Cite Article Cite Article

MLA

Pritham Sriram G., et al. "Modified GAN for Natural Occlusion Detection and Inpainting of Raw Footage From Video Surveillance." IJBDIA vol.3, no.1 2022: pp.1-18. http://doi.org/10.4018/IJBDIA.312852

APA

Pritham Sriram G., Prasana Venkatesh S., Deepak Raj P., & Gladston, A. (2022). Modified GAN for Natural Occlusion Detection and Inpainting of Raw Footage From Video Surveillance. International Journal of Big Data Intelligence and Applications (IJBDIA), 3(1), 1-18. http://doi.org/10.4018/IJBDIA.312852

Chicago

Pritham Sriram G., et al. "Modified GAN for Natural Occlusion Detection and Inpainting of Raw Footage From Video Surveillance," International Journal of Big Data Intelligence and Applications (IJBDIA) 3, no.1: 1-18. http://doi.org/10.4018/IJBDIA.312852

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Low resolution and occlusion are mainly prominent in images taken from certain unconstrained environments such as raw footage from video surveillance. In this work, a deep generative adversarial network for joint face completion and face super-resolution is proposed. It will be really useful in the current COVID-19 scenario as people wearing masks are a common sight. Given an input of a low-resolution face image with occlusion, the generator aims to recover a high-resolution face image without occlusion. The discriminator uses a set of carefully designed losses to assure the high quality of the recovered high-resolution face images without occlusion. Experimental results on CelebA database show that the proposed approach outperforms the state-of-the-art methods in jointly performing face super-resolution and face completion, and shows good generalization ability in cross-database testing. MSSIM showed an accuracy of around 80% for test cases. The recorded values of generator adversarial loss, generator pixel loss, and discriminator loss are 0.93, 0.10, and 0.003, respectively.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.