影像科学与光化学 ›› 2012, Vol. 30 ›› Issue (2): 142-149.DOI: 10.7517/j.issn.1674-0475.2012.02.142

• 应用与发展 • 上一篇    下一篇

基于样本库的人脸图像处理方法

黎智辉1, 彭思龙2, 王永强1, 许小京1   

  1. 1. 公安部 物证鉴定中心, 北京 100038;
    2. 中国科学院 自动化研究所, 北京 100190
  • 收稿日期:2011-09-23 修回日期:2012-01-05 出版日期:2012-03-15 发布日期:2012-03-15
  • 通讯作者: 彭思龙,E-mail:Silong.peng@ia.ac.cn.

Human Face Super-Resolution Method Based on Train-Database

LI Zhi-hui1, PENG Si-long2, WANG Yong-qiang1, XU Xiao-jing1   

  1. 1. Institute of Forensic Science. Ministry of Public Security, Beijing 100038, P.R.China;
    2. Institute of Automation, Chinese Academy of Sciences, Beijing 100190, P.R.China;
  • Received:2011-09-23 Revised:2012-01-05 Online:2012-03-15 Published:2012-03-15

摘要: 本文给出了一种基于样本库的人脸图像超分辨率方法,这一方法结合了人脸图像全局相似性和局部特征相似性的约束.局部结构的相似性将超分辨率解约束到人脸局部结构空间,不同尺度上的局部相似性指导搜索最优解,然后将局部结构重建的人脸图像投影到由人脸图像确定的特征人脸空间.实验结果表明该算法得到的人脸具有很好的准确性和视觉效果.

关键词: 图像超分辨率, 人脸样本库, 局部结构相似性, 结构搜索, 投影

Abstract: In this paper, we propose a human face super-resolution method based on training. This method composes similarity constrains of human face both in global and local manner. The local structure of human face ensures the solution of super-resolution to be in the space characterized by human face local structure. And the local structure in different scales instruct the searching to the optimal solution, then project the reconstructed face by local structure to the eigenface space determined by given human face database. Experiments show that the results have very good accuracy and high visual quality.

Key words: image super-resolution, human face database, similarity of human face in local structure, structure searching, project

中图分类号: