Analysis and Synthesis of Multi-layered Facial Detail
碩士 === 國立交通大學 === 多媒體工程研究所 === 96 === This thesis presents a multi-layer analysis and synthesis approach to synthesize novel expressions with fine facial details and global features. We analyze correlation between different face regions as the criterion for face segmentation, and process each sub-re...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2008
|
Online Access: | http://ndltd.ncl.edu.tw/handle/87680359527755593660 |
id |
ndltd-TW-096NCTU5641021 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-096NCTU56410212015-10-13T13:51:51Z http://ndltd.ncl.edu.tw/handle/87680359527755593660 Analysis and Synthesis of Multi-layered Facial Detail 多層次臉部細紋之分析與合成 Jia-Ru Lin 林家如 碩士 國立交通大學 多媒體工程研究所 96 This thesis presents a multi-layer analysis and synthesis approach to synthesize novel expressions with fine facial details and global features. We analyze correlation between different face regions as the criterion for face segmentation, and process each sub-region independently for generating various appearances. In synthesis procedure, we use the high-band enhancement steerable pyramid for decomposing various frequency components. The lowest sub-band is used for primary deformation by blend shape. For high-band, the statistic-based feature matching and high-band enhancement synthesis is applied. Due to our high-band\low-band separate procedures, we can synthesize photorealistic facial expressions. Integrate our approach with spatial-temporal constraints and texture alignment, we can generate detail-preserved facial animation. I-Chen Lin 林奕成 2008 學位論文 ; thesis 46 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立交通大學 === 多媒體工程研究所 === 96 === This thesis presents a multi-layer analysis and synthesis approach to synthesize novel expressions with fine facial details and global features. We analyze correlation between different face regions as the criterion for face segmentation, and process each sub-region independently for generating various appearances. In synthesis procedure, we use the high-band enhancement steerable pyramid for decomposing various frequency components. The lowest sub-band is used for primary deformation by blend shape. For high-band, the statistic-based feature matching and high-band enhancement synthesis is applied. Due to our high-band\low-band separate procedures, we can synthesize photorealistic facial expressions. Integrate our approach with spatial-temporal constraints and texture alignment, we can generate detail-preserved facial animation.
|
author2 |
I-Chen Lin |
author_facet |
I-Chen Lin Jia-Ru Lin 林家如 |
author |
Jia-Ru Lin 林家如 |
spellingShingle |
Jia-Ru Lin 林家如 Analysis and Synthesis of Multi-layered Facial Detail |
author_sort |
Jia-Ru Lin |
title |
Analysis and Synthesis of Multi-layered Facial Detail |
title_short |
Analysis and Synthesis of Multi-layered Facial Detail |
title_full |
Analysis and Synthesis of Multi-layered Facial Detail |
title_fullStr |
Analysis and Synthesis of Multi-layered Facial Detail |
title_full_unstemmed |
Analysis and Synthesis of Multi-layered Facial Detail |
title_sort |
analysis and synthesis of multi-layered facial detail |
publishDate |
2008 |
url |
http://ndltd.ncl.edu.tw/handle/87680359527755593660 |
work_keys_str_mv |
AT jiarulin analysisandsynthesisofmultilayeredfacialdetail AT línjiārú analysisandsynthesisofmultilayeredfacialdetail AT jiarulin duōcéngcìliǎnbùxìwénzhīfēnxīyǔhéchéng AT línjiārú duōcéngcìliǎnbùxìwénzhīfēnxīyǔhéchéng |
_version_ |
1717744745517678592 |