结合位置先验与稀疏表示的单帧人脸图像超分辨率算法

计算机应用 ›› 2012, Vol. 32 ›› Issue (05): 1300-1302.

结合位置先验与稀疏表示的单帧人脸图像超分辨率算法

马祥¹,²

1. 长安大学信息工程学院，西安 710064
2. 西安交通大学电子与信息工程学院，西安 710049

收稿日期:2011-10-25 修回日期:2011-12-08 发布日期:2012-05-01 出版日期:2012-05-01
通讯作者: 马祥
作者简介:马祥(1978-)，男，甘肃平凉人，讲师，博士，主要研究方向：图像分辨率增强与识别。
基金资助:
国家自然科学基金资助项目（61101215);中央高校基本科研业务费专项资金资助项目（CHD2011JC146）;长安大学基础研究支持计划专项基金资助项目

Face hallucination based on position prior and sparse representation

MA Xiang¹,²

1. School of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an Shaanxi 710049, China
2. School of Information Engineering, Chang'an University, Xi'an Shaanxi 710064, China

Received:2011-10-25 Revised:2011-12-08 Online:2012-05-01 Published:2012-05-01
Contact: MA Xiang

摘要/Abstract

摘要： 提出了一种结合位置先验与稀疏表示的人脸图像超分辨率算法，可对单帧输入的低分辨率人脸图像基于训练集进行超分辨率重建。利用压缩感知理论中的信号分解方法，〖BP(〗明确哪些方法更好〖BP)〗，将稀疏表示与人脸位置先验信息相结合，使用经过分类的超完备冗余字典，来分别稀疏逼近输入信号的块向量结构。利用最佳的K项原子，线性组合重建出高分辨率图像块。最后按照图像块最初在人脸的位置，将它们拼接为整体人脸。在CAS-PEAL-R1人脸图库上的实验结果表明，该算法使用相对较少的原子，就可以重建出质量较好的高分辨率人脸图像。

关键词: 稀疏表示, 压缩感知, 超完备字典, 位置先验, 人脸图像, 超分辨率

Abstract: A face hallucination method based on sparse representation and position prior was proposed, which can obtain the enlargement of a single low-resolution input. Some perspectives of compressed sensing were applied to the method. The high- and low-resolution over-complete atoms were classified according to different positions of face. The low-resolution face image inputs were approximated by the sparse linear combination of the over-complete atoms which were classified. The sparse coefficients were obtained to reconstruct the high-resolution data of certain position. According to their original positions, the generated patches were integrated into a global face. The experimental results illustrate that the proposed method can generate satisfying high-resolution face image using fewer atoms compared to other methods.

Key words: sparse representation, compressed sensing, over-complete dictionary, position prior, face image, super-resolution

中图分类号:

TP391.41

马祥. 结合位置先验与稀疏表示的单帧人脸图像超分辨率算法[J]. 计算机应用, 2012, 32(05): 1300-1302.

MA Xiang. Face hallucination based on position prior and sparse representation[J]. Journal of Computer Applications, 2012, 32(05): 1300-1302.

参考文献

［1］DONOHO L D. Compressed sensing ［J］. IEEE Transactions on Information Theory, 2006, 52(4):1289-1306.

［2］TEMLYAKOV V. Nonlinear methods of approximation ［R］. Los Angeles: University of South Carolina, Department of Mathematics, 2001.

［3］MALLAT S, ZHANG Z. Matching pursuits with time-frequency dictionaries ［J］. IEEE Transactions on Signal Processing, 1993, 41(12): 3397-3415.

［4］TROPP J A, GILBERT A C. Signal recovery from partial In-formation by orthogonal matching pursuit ［EB/OL］.(2005)[2011-10-01]. http://www.personal. umich. edu/ - jtropp/ papers/ TG052Signal2Re2 covery. pdf.

［5］CHEN S S, DONOHO D L, SAUNDERS M A. Atomicdecomposition by basis pursuit ［J］. SIAM Journal on Scientific Computing, 2001, 43(1): 129-159.

［6］DONOHO D L, ELAD M. Optimally sparse representation ingeneral (non-orthogonal) dictionaries via l1 minimization ［EB/OL］.［2011-09-08］. http://www-stat.stanford.edu/~donoho/Reports/2002/OptSparse.pdf.

［7］AHARON M, ELAD M, BRUCKSTEIN A. K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation ［J］. IEEE Transactions on Signal Processing, 2006, 23(4): 4311-4322.

［8］GAO WEN, CAO BO, SHAN SHIQUAN, et al.The CAS-PEAL large-scale Chinese face database and baseline evaluations ［J］. IEEE Transactions on System Man, and Cybernetics: Part A, 2008, 38(1):149-161.

［9］MA X, ZHANG J P, QI C. Hallucinating face by position-patch ［J］. Pattern Recognition, 2010, 43(6): 2224-2236.

［10］WANG X G, TANG X O. Hallucinating face by eigen trans-formation ［J］. IEEE Transactions on Systems, Man and Cybernetics, 2005, 35(3): 425-434.

［11］CHANG H, YEUNG D Y, XIONG Y M. Super-resolution through neighbor embedding ［C］// Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE, 2004: 1275-1282.

［12］ZHUANG Y T, ZHANG J, WU F. Hallucinating faces: LPH super- resolution and neighbor reconstruction for residue compensation ［J］. Pattern Recognition, 2007, 40(9):3178-3194.

[1]	裴春阳, 樊宽刚, 马政. 基于边缘保留分解和改进稀疏表示的医学图像融合[J]. 计算机应用, 2021, 41(7): 2092-2099.
[2]	牛康力, 谌雨章, 沈君凤, 曾张帆, 潘永才, 王绎冲. 基于深度学习的双通道夜视图像复原方法[J]. 计算机应用, 2021, 41(6): 1775-1784.
[3]	梁敏, 王昊榕, 张瑶, 李杰. 基于加速残差网络的图像超分辨率重建方法[J]. 计算机应用, 2021, 41(5): 1438-1444.
[4]	段友祥, 张含笑, 孙歧峰, 孙友凯. 基于拉普拉斯金字塔生成对抗网络的图像超分辨率重建算法[J]. 计算机应用, 2021, 41(4): 1020-1026.
[5]	卞鹏程, 郑忠龙, 李明禄, 何依然, 王天翔, 张大伟, 陈丽媛. 基于注意力融合网络的视频超分辨率重建[J]. 计算机应用, 2021, 41(4): 1012-1019.
[6]	任晓奎, 刘鹏飞, 陶志勇, 刘影, 白立春. 基于单快拍信号到达角估计算法的室内入侵检测[J]. 计算机应用, 2021, 41(4): 1153-1159.
[7]	王永金, 左羽, 吴恋, 崔忠伟, 赵晨洁. 基于注意力机制的图像超分辨率重建[J]. 计算机应用, 2021, 41(3): 845-850.
[8]	李萌, 秦品乐, 曾建潮, 李俊伯. 基于磁共振影像层间插值的超分辨率及多视角融合[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3362-3367.
[9]	沈子懿, 王卫亚, 蒋东华, 荣宪伟. 基于Hopfield混沌神经网络和压缩感知的可视化图像加密算法[J]. 计算机应用, 2021, 41(10): 2893-2899.
[10]	王丽娟, 陈少敏, 尹明, 许跃颖, 郝志峰, 蔡瑞初, 温雯. 基于近邻图改进的块对角子空间聚类算法[J]. 计算机应用, 2021, 41(1): 36-42.
[11]	林静, 黄玉清, 李磊民. 基于球形矩匹配与特征判别的图像超分辨率重建[J]. 计算机应用, 2020, 40(8): 2345-2350.
[12]	胡高鹏, 陈子鎏, 王晓明, 张开放. 基于深度渐进式反投影注意力网络的图像超分辨率重建[J]. 计算机应用, 2020, 40(7): 2077-2083.
[13]	胡雪影, 郭海儒, 朱蓉. 基于混合深度卷积网络的图像超分辨率重建[J]. 计算机应用, 2020, 40(7): 2069-2076.
[14]	席雅睿, 乔志伟, 温静, 张艳娇, 杨雯晶, 闫慧文. 基于Chambolle-Pock算法框架的高阶TV图像重建算法[J]. 计算机应用, 2020, 40(6): 1793-1798.
[15]	代强, 程曦, 王永梅, 牛子未, 刘飞. 基于轻量自动残差缩放网络的图像超分辨率重建[J]. 计算机应用, 2020, 40(5): 1446-1452.