Facial Skin Beautification Using Adaptive Region-Aware Masks

doi:10.1109/TCYB.2014.2311033

OPT OpenIR > 光谱成像技术研究室

	Facial Skin Beautification Using Adaptive Region-Aware Masks
	Liang, Lingyu 1; Jin, Lianwen 1; Li, Xuelong2
作者部门	光学影像学习与分析中心
	2014-12-01
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
ISSN	2168-2267
卷号	44 期号:12 页码:2600-2612
产权排序	2
摘要	In this paper, we propose a unified facial beautification framework with respect to skin homogeneity, lighting, and color. A novel region-aware mask is constructed for skin manipulation, which can automatically select the edited regions with great precision. Inspired by the state-of-the-art edit propagation techniques, we present an adaptive edge-preserving energy minimization model with a spatially variant parameter and a high-dimensional guided feature space for mask generation. Using region-aware masks, our method facilitates more flexible and accurate facial skin enhancement while the complex manipulations are simplified considerably. In our beautification framework, a portrait is decomposed into smoothness, lighting, and color layers by an edge-preserving operator. Next, facial landmarks and significant features are extracted as input constraints for mask generation. After three region-aware masks have been obtained, a user can perform facial beautification simply by adjusting the skin parameters. Furthermore, the combinations of parameters can be optimized automatically, depending on the data priors and psychological knowledge. We performed both qualitative and quantitative evaluation for our method using faces with different genders, races, ages, poses, and backgrounds from various databases. The experimental results demonstrate that our technique is superior to previous methods and comparable to commercial systems, for example, PicTreat, Portrait+, and Portraiture.
文章类型	Article
关键词	Edge-preserving Smoothing Edit Propagation Face Beautification Facial Attractiveness Image Editing Region-aware Mask
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCYB.2014.2311033
收录类别	SCI ; EI
关键词[WOS]	FACE DETECTION ; ATTRACTIVENESS ; BEAUTY ; FEATURES ; COLOR
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000345629000029
引用统计	被引频次：32[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/22415
专题	光谱成像技术研究室
作者单位	1.S China Univ Technol, Sch Elect & Informat Engn, Guangzhou 510641, Guangdong, Peoples R China 2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr Opt Imagery Anal & Learning OPTIMAL, Xian 710119, Peoples R China
推荐引用方式 GB/T 7714	Liang, Lingyu,Jin, Lianwen,Li, Xuelong. Facial Skin Beautification Using Adaptive Region-Aware Masks[J]. IEEE TRANSACTIONS ON CYBERNETICS,2014,44(12):2600-2612.
APA	Liang, Lingyu,Jin, Lianwen,&Li, Xuelong.(2014).Facial Skin Beautification Using Adaptive Region-Aware Masks.IEEE TRANSACTIONS ON CYBERNETICS,44(12),2600-2612.
MLA	Liang, Lingyu,et al."Facial Skin Beautification Using Adaptive Region-Aware Masks".IEEE TRANSACTIONS ON CYBERNETICS 44.12(2014):2600-2612.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Facial Skin Beautifi（1820KB）	期刊论文	出版稿	限制开放	CC BY	请求全文