A Novel Efficient Deep Learning Framework for Facial Inpainting
Publication Date
1-1-2023
Document Type
Conference Proceeding
Publication Title
Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023
DOI
10.1109/CAI54212.2023.00096
First Page
203
Last Page
204
Abstract
The usage of masks during the pandemic has made identifying criminals using surveillance cameras very difficult. Generating the facial features behind a mask is a type of image inpainting. Current research on image inpainting shows promising results on manually pixelated regular holes/patches but has not been designed to handle the specific case of 'unmasking' faces. In this paper we propose a novel, custom U-Net based Convolutional Neural Network to regenerate the face under a mask. Simulation results demonstrate that our proposed framework can achieve more than 97% Structural Similarity Index Measure for different types of facial masks across different faces, irrespective of gender, race or color.
Keywords
CNN, decoder, encoder, GAN, inpainting, U-Net
Department
Computer Science
Recommended Citation
Akshay Ravi, Navrati Saxena, Abhishek Roy, and Srajan Gupta. "A Novel Efficient Deep Learning Framework for Facial Inpainting" Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023 (2023): 203-204. https://doi.org/10.1109/CAI54212.2023.00096
