Digital makeup using machine learning algorithms

In this report, we present a pipeline system of digital makeup for industry scenarios. The pipeline contains two parts: i) facial feature semantic segmentation; ii) colour transfer. For facial feature semantic segmentation task, we adopt fully convolutional network (FCN) with weighted cross entropy...

全面介紹

Saved in:

書目詳細資料
主要作者:	Wu, Sibing
其他作者:	He Ying
格式:	Final Year Project
語言:	English
出版:	Nanyang Technological University 2022
主題:	Engineering::Computer science and engineering
在線閱讀:	https://hdl.handle.net/10356/156504
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!
機構:	Nanyang Technological University
語言:	English

id	sg-ntu-dr.10356-156504
record_format	dspace
spelling	sg-ntu-dr.10356-1565042022-04-19T05:06:56Z Digital makeup using machine learning algorithms Wu, Sibing He Ying School of Computer Science and Engineering YHe@ntu.edu.sg Engineering::Computer science and engineering In this report, we present a pipeline system of digital makeup for industry scenarios. The pipeline contains two parts: i) facial feature semantic segmentation; ii) colour transfer. For facial feature semantic segmentation task, we adopt fully convolutional network (FCN) with weighted cross entropy as loss function during training; for colour transfer task, we experimented N-dimensional Probability Density Function transfer algorithm, a fast exemplar-based image colourisation approach using colour embeddings named Color2Embed, and deep exemplar-bases colourisation approach. Considering economical and qualitative factors, we conclude that model trained by VGG16 FCN with weighted cross entropy together with fast exemplar-based image colourisation yields the most suitable result. Bachelor of Engineering (Computer Science) 2022-04-19T05:06:56Z 2022-04-19T05:06:56Z 2022 Final Year Project (FYP) Wu, S. (2022). Digital makeup using machine learning algorithms. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156504 https://hdl.handle.net/10356/156504 en SCSE21-0009 application/pdf Nanyang Technological University
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
language	English
topic	Engineering::Computer science and engineering
spellingShingle	Engineering::Computer science and engineering Wu, Sibing Digital makeup using machine learning algorithms
description	In this report, we present a pipeline system of digital makeup for industry scenarios. The pipeline contains two parts: i) facial feature semantic segmentation; ii) colour transfer. For facial feature semantic segmentation task, we adopt fully convolutional network (FCN) with weighted cross entropy as loss function during training; for colour transfer task, we experimented N-dimensional Probability Density Function transfer algorithm, a fast exemplar-based image colourisation approach using colour embeddings named Color2Embed, and deep exemplar-bases colourisation approach. Considering economical and qualitative factors, we conclude that model trained by VGG16 FCN with weighted cross entropy together with fast exemplar-based image colourisation yields the most suitable result.
author2	He Ying
author_facet	He Ying Wu, Sibing
format	Final Year Project
author	Wu, Sibing
author_sort	Wu, Sibing
title	Digital makeup using machine learning algorithms
title_short	Digital makeup using machine learning algorithms
title_full	Digital makeup using machine learning algorithms
title_fullStr	Digital makeup using machine learning algorithms
title_full_unstemmed	Digital makeup using machine learning algorithms
title_sort	digital makeup using machine learning algorithms
publisher	Nanyang Technological University
publishDate	2022
url	https://hdl.handle.net/10356/156504
_version_	1731235745334558720

Digital makeup using machine learning algorithms

相似書籍