Manifold learning-based sample selection method for facial image super-resolution
Zhang, Xuesong; Jiang, Jing; Li, Junhong; et al.
发表期刊OPTICAL ENGINEERING
2012-04-01
卷号51期号:4
文章类型Article
摘要Learning efficiency, related to not only the size of training set but also to the usage of samples, is an important issue of learning-based super-resolution (SR). We propose a face hallucination method with adaptive sample selection ability by learning from the facial manifold. Employing locality preserving projections (LPP) to analyze the intrinsic features on the local facial manifold, our method searches out image patches dynamically in the LPP subspace, which makes the training set tailored to the input patch. Using the selected training set, we develop a patch-based eigen-transformation algorithm to efficiently restore the lost high-frequency components of the low-resolution face image. Experiments on synthetic and real-life images fully demonstrate that the proposed adaptive sample selection SR method can achieve better performance than some state-of-the-art learning-based SR techniques with less computational cost by utilizing a relative small sample, especially under the case of low quality input images.
关键词Super-resolution Face Image Locality Preserving Projections Manifold Learning Unsupervised Learning
WOS标题词Science & Technology ; Physical Sciences
关键词[WOS]FACE ; RECONSTRUCTION ; HALLUCINATION
收录类别SCI
语种英语
WOS研究方向Optics
WOS类目Optics
WOS记录号WOS:000304015100055
引用统计
被引频次:2[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/2919
专题智能制造技术与系统研究中心_多维数据分析(彭思龙)-技术团队
通讯作者Zhang, Xuesong
推荐引用方式
GB/T 7714
Zhang, Xuesong,Jiang, Jing,Li, Junhong,et al. Manifold learning-based sample selection method for facial image super-resolution[J]. OPTICAL ENGINEERING,2012,51(4).
APA Zhang, Xuesong,Jiang, Jing,Li, Junhong,&et al..(2012).Manifold learning-based sample selection method for facial image super-resolution.OPTICAL ENGINEERING,51(4).
MLA Zhang, Xuesong,et al."Manifold learning-based sample selection method for facial image super-resolution".OPTICAL ENGINEERING 51.4(2012).
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang, Xuesong]的文章
[Jiang, Jing]的文章
[Li, Junhong]的文章
百度学术
百度学术中相似的文章
[Zhang, Xuesong]的文章
[Jiang, Jing]的文章
[Li, Junhong]的文章
必应学术
必应学术中相似的文章
[Zhang, Xuesong]的文章
[Jiang, Jing]的文章
[Li, Junhong]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。