期刊文献+

基于MAP框架的金字塔人脸超分辨率算法 被引量:3

Pyramid Face Supper-resolution Algorithm Based on MAP Frame
下载PDF
导出
摘要 提出一种基于学习的金字塔人脸超分辨率算法,利用金字塔学习人脸图像梯度的空间分布特性,建立标准人脸训练库作为学习模型,采用塔状父结构从训练库搜索匹配特征信息相似度最高的小块,预测出最优的拉普拉斯金字塔先验模型,利用贝叶斯MAP框架求出高分辨率人脸图像。实验结果表明,与其他人脸超分辨率算法相比,在将人脸图像分辨率提高4×4倍的情况下,该算法生成的高分辨率人脸图像的平均峰值信噪比提高1.19 dB^2.4 dB,可以更好地消除噪声,具有较好的视觉效果。 A new learning-based super-resolution algorithm is presented.Pyramid is used to extract the facial gradient distribution features,the standard face training database is established for the study model,these features are combined with pyramid-like parent structure to predict the best prior.And through the Bayesian Maximum A Posterior(MAP) frame,the high resolution face image is captured.Experimental results show that the proposed algorithm synthesizes high-resolution faces and eliminates the noise with better visual effect,and the average of peak signal-to-noise ratios is improved about 1.19 dB to 2.4 dB compared with some existing face super-resolution algorithms.
出处 《计算机工程》 CAS CSCD 2012年第10期206-208,211,共4页 Computer Engineering
基金 河北省教育厅基金资助重点项目(ZD200911)
关键词 超分辨率 贝叶斯 最大后验概率 金字塔 父结构 super-resolution Bayesian MaximumAPosterior(MAP) pyramid parent structure
  • 相关文献

参考文献7

二级参考文献24

共引文献8

同被引文献29

  • 1浦剑,张军平,黄华.超分辨率算法研究综述[J].山东大学学报(工学版),2009,39(1):27-32. 被引量:35
  • 2Tsai R Y,Huang T S.Multipleframe Image Restoration and Registration[C]//Proc.of Conference on Advances in Computer Vision and Image Processing.Greenwich,USA:JAI Press Inc.,1984:317-339. 被引量:1
  • 3Stark H,Oskoui P.High-resolution Image Recovery from Image-plane Arrays,Using Convex Projections[J].Journal of the Optical Society of America A,1989,6(11):1715-1726. 被引量:1
  • 4Freeman W T,Jones T R,Pasztor E C.Example-based Super-resolution[J].IEEE Computer Graphics and Applications,2002,22 (2):56-65. 被引量:1
  • 5Chang Hong,Yeung D Y,Xiong Yimin.Super-resolution Through Neighbor Embedding[C]//Proc.of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:[s.n.],2004:275-282. 被引量:1
  • 6Irani M,Peleg S.Improving Resolution by Image Registration[J].CVGIP:Graphical Models and Image Processing,1991,53 (3):231-239. 被引量:1
  • 7Baker S,Kanade T.Limits on Super-resolution and How to Break Them[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24 (9):1167-1183. 被引量:1
  • 8Glasner D,Bagon S,Irani M.Super-resolution from a Single Image[C]//Proc.of the 12th International Conference on Computer Vision.Kyoto,Japan:[s.n.],2009:349-356. 被引量:1
  • 9Barnes C,Shechtman E,Goldman D B,et al.The Generalized Patch Match Correspondence Algorithm[C]//Proc.of the 11th European Conference on Computer Vision.Heraklion,Greece:[s.n.],2010:29-43. 被引量:1
  • 10Arya S,Mount D M.Approximate Nearest Neighbor Queries in Fixed Dimensions[C]//Proc.of the 4th Annual ACM-SIAM Symposium on Discrete Algorithms.Philadelphia,USA:[s.n.],1993:271-280. 被引量:1

引证文献3

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部