中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 软件研究所
  3. 软件所图书馆
  4. 会议论文
smoothness-constrained face photo-sketch synthesis using sparse representation

文献类型：会议论文

作者Chang Liang ; Deng Xiaoming ; Zhou Mingquan ; Duan Fuqing ; Wu Zhongke
出版日期2012
会议名称21st International Conference on Pattern Recognition, ICPR 2012
会议日期November 11, 2012 - November 15, 2012
会议地点Tsukuba, Japan
关键词Convex optimization Optimization Pattern recognition
页码3025-3029
中文摘要Face photo-sketch and sketch-photo synthesis have important usages in law enforcement. It is challenging to synthesize face sketches from photos because the drawing techniques and styles of artists' depictions are hard to be learned. To synthesize face photos from sketches is also hard due to its ill-posed nature. In order to avoid mosaic effects in the existed photo-sketch methods, we propose a smoothness-constrained photo-sketch synthesis method via sparse representation. The work is an extension of the previous work[1]. The method is modeled as the minimization of an energy function, a large scale convex optimization problem with l1-norm constraint. Since previous optimization methods are infeasible to solve our problem, we propose an iterative optimization approach, which decomposes the large scale optimization into a sequence of small scale optimizations and solve them iteratively to obtain the approximated optimal solution. The same synthesis strategy can be also used to synthesize photos from sketches. Experiments show its effectiveness. © 2012 ICPR Org Committee.
英文摘要Face photo-sketch and sketch-photo synthesis have important usages in law enforcement. It is challenging to synthesize face sketches from photos because the drawing techniques and styles of artists' depictions are hard to be learned. To synthesize face photos from sketches is also hard due to its ill-posed nature. In order to avoid mosaic effects in the existed photo-sketch methods, we propose a smoothness-constrained photo-sketch synthesis method via sparse representation. The work is an extension of the previous work[1]. The method is modeled as the minimization of an energy function, a large scale convex optimization problem with l1-norm constraint. Since previous optimization methods are infeasible to solve our problem, we propose an iterative optimization approach, which decomposes the large scale optimization into a sequence of small scale optimizations and solve them iteratively to obtain the approximated optimal solution. The same synthesis strategy can be also used to synthesize photos from sketches. Experiments show its effectiveness. © 2012 ICPR Org Committee.
收录类别EI
会议主办者Science Council of Japan; Information Processing Society of Japan (IPSJ); Inst. Electron., Inf. Commun. Eng. (IEICE) Inf. Syst. Soc. (ISS); Japan Society for the Promotion of Science (JSPS); The Telecommunications Advancement Foundation
会议录Proceedings - International Conference on Pattern Recognition
语种英语
ISSN号1051-4651
ISBN号9784990644109
源URL[http://ir.iscas.ac.cn/handle/311060/15982]  
专题软件研究所_软件所图书馆_会议论文
推荐引用方式
GB/T 7714		 Chang Liang,Deng Xiaoming,Zhou Mingquan,et al. smoothness-constrained face photo-sketch synthesis using sparse representation[C]. 见:21st International Conference on Pattern Recognition, ICPR 2012. Tsukuba, Japan. November 11, 2012 - November 15, 2012.

入库方式： OAI收割

来源：软件研究所

浏览0
下载0
收藏0
其他版本

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。