Remove specular highlight from facial images using deep learning

In this paper, I present an image pre-processing technique, known as specular highlight removal in facial images. In comparison to previous works that depend on physical and statistical properties of human skin and faces, I propose a deep learning algorithm using autoencoder to generate highlight-fr...

Full description

Bibliographic Details
Main Author: Ooi, Yue Ying
Other Authors: Cham Tat Jen
Format: Final Year Project (FYP)
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/148186
_version_ 1826117511637106688
author Ooi, Yue Ying
author2 Cham Tat Jen
author_facet Cham Tat Jen
Ooi, Yue Ying
author_sort Ooi, Yue Ying
collection NTU
description In this paper, I present an image pre-processing technique, known as specular highlight removal in facial images. In comparison to previous works that depend on physical and statistical properties of human skin and faces, I propose a deep learning algorithm using autoencoder to generate highlight-free/diffuse facial images. By taking facial images with specular highlight as the input, the autoencoder model that has been trained on the corresponding diffuse images will attempt to reconstruct diffuse images from the features that it has learned. The results obtained in this project demonstrate a good learning efficiency and reliable reconstruction of the facial image. I have also built a dataset of synthetic facial images in a different lighting environment that was used in this facial highlight removal experiment.
first_indexed 2024-10-01T04:28:48Z
format Final Year Project (FYP)
id ntu-10356/148186
institution Nanyang Technological University
language English
last_indexed 2024-10-01T04:28:48Z
publishDate 2021
publisher Nanyang Technological University
record_format dspace
spelling ntu-10356/1481862021-04-26T06:31:18Z Remove specular highlight from facial images using deep learning Ooi, Yue Ying Cham Tat Jen School of Computer Science and Engineering ASTJCham@ntu.edu.sg Engineering::General In this paper, I present an image pre-processing technique, known as specular highlight removal in facial images. In comparison to previous works that depend on physical and statistical properties of human skin and faces, I propose a deep learning algorithm using autoencoder to generate highlight-free/diffuse facial images. By taking facial images with specular highlight as the input, the autoencoder model that has been trained on the corresponding diffuse images will attempt to reconstruct diffuse images from the features that it has learned. The results obtained in this project demonstrate a good learning efficiency and reliable reconstruction of the facial image. I have also built a dataset of synthetic facial images in a different lighting environment that was used in this facial highlight removal experiment. Bachelor of Engineering (Computer Science) 2021-04-26T06:31:18Z 2021-04-26T06:31:18Z 2021 Final Year Project (FYP) Ooi, Y. Y. (2021). Remove specular highlight from facial images using deep learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/148186 https://hdl.handle.net/10356/148186 en SCSE20-0478 application/pdf Nanyang Technological University
spellingShingle Engineering::General
Ooi, Yue Ying
Remove specular highlight from facial images using deep learning
title Remove specular highlight from facial images using deep learning
title_full Remove specular highlight from facial images using deep learning
title_fullStr Remove specular highlight from facial images using deep learning
title_full_unstemmed Remove specular highlight from facial images using deep learning
title_short Remove specular highlight from facial images using deep learning
title_sort remove specular highlight from facial images using deep learning
topic Engineering::General
url https://hdl.handle.net/10356/148186
work_keys_str_mv AT ooiyueying removespecularhighlightfromfacialimagesusingdeeplearning