A Super-Resolution Method for Face Images Using Position-Dictionary Pairs

您当前的位置：

首页 >

文章列表页 >

A Super-Resolution Method for Face Images Using Position-Dictionary Pairs

更新时间：2025-07-09

- A Super-Resolution Method for Face Images Using Position-Dictionary Pairs
- Vol. 46, Issue 6, Pages: 7-11(2012)
- 作者机构：
  
  西安交通大学电子与信息工程学院,西安,710049
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN911.73
- Online First：10 June 2012，
  
  Published：2012
- 稿件说明：
移动端阅览
A Super-Resolution Method for Face Images Using Position-Dictionary Pairs[J]. 2012, 46(6): 7-11.
DOI：

A Super-Resolution Method for Face Images Using Position-Dictionary Pairs[J]. 2012, 46(6): 7-11. DOI：

摘要

针对基于稀疏表示的人脸超分辨率算法存在的字典尺寸大、训练时间长等问题

提出一种基于位置字典对的超分辨率重建方法.由于同一位置的人脸图像块具有相似的结构和内容

更有可能用相同的字典原子进行线性组合表示

因此把训练人脸图像按位置分块

首先为每个位置训练一个位置字典对

利用获得的多个位置字典对

对低分辨率测试人脸图像进行基本重建

然后应用残差补偿方法对位置块进行补偿.实验结果表明

由所提方法重建的人脸图像具有更好的视觉效果

与应用原始图像块进行稀疏表示的图像超分辨率算法相比

平均图像结构相似度指标值提高了0.082

同时字典训练时间缩短了约5倍.

Abstract

A novel method using position-dictionary pairs is proposed to reconstruct a high resolution frontal face image from a single low resolution version. Since the contents and structures in the same position of face image patches are similar and are more likely to be better represented by the combination of the same dictionary atoms

face images used for training are blocked into overlapped position-patches. Then a small position-dictionary pair is trained for each position. A basic high resolution image can be recovered for each low resolution input by using these position-dictionary pairs. Finally

the visual quality of the reconstructed image is improved by using a residual compensation method. Experimental results show that face images reconstructed by the proposed method have better visual effect. A comparison with the algorithm of image super-resolution via raw image patches based sparse representation show that the SSIM of the proposed method is 0.082 higher; while the training time is shortened about 5 times.

关键词

Keywords

references

FARSIU S, ROBINSON M D, ELAD M, et al. Fast and robust multiframe super resolution [J]. IEEE Transaction on Image Processing, 2004, 13(10):1327-1344.

IRANI M, PELEG S. Super resolution from image sequences [C]∥10th International Conference on Pattern Recognition. Piscataway, NJ, USA: IEEE,1990:115-120.

GLASNER D, BAGON S, RANI M. Super-resolution from a single image [C]∥IEEE 12th International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2009: 349-356.

PICKUP L C. Machine learning in multi-frame image super resolution [EB/OL].(2009-03-12)[2011-12-10]. http:∥www.robots.ox.ac.uk/～vgg/publications/2008/Pickup08/.

MAIRAL J, ELAD M, SAPIRO G. Sparse representation for color image restoration [J]. IEEE Transaction on Image Processing, 2007, 17(1):53-69.

HUANG Hua, WU Ning. Fast facial image super-resolution via local linear transformations for resources limited applications [J]. IEEE Transaction on Circuits and Systems for Video Technology, 2011,21(10):1363-1377.

ROBINSON D, MILANFAR P. Fundamental performance limits in image registration [J]. IEEE Transaction on Image Processing, 2004, 13(9):1185-1199.

YANG Jianchao, WRIGHT J, MA Yi. Image super-resolution as sparse representation of raw image patches [C]∥2008 Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2008: 1-8.

DONG Weisheng, ZHANG Lei, SHI Guangming. Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization [J]. IEEE Transaction on Image Processing, 2011, 20(7): 1838-1857.

HUANG Junzhou, ZHANG Tang, METACAS D. Learning with structured sparsity [C]∥ICML'09 Proceedings of the 26th Annual International Conference on Machine Learning. New York, USA: ACM, 2009:417-424.

HUANG Junzhou, HUANG Xiaolei, METAXAS D. Learning with dynamic group sparsity [C]∥2009 IEEE 12th International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2009:64-71.

LEE H, BATTLE A, RAINA R, et al. Efficient sparse coding algorithms [J]. Advances in Neural Information Processing Systems,2007,19(2):801-808.

马祥,齐春.全局重建和位置块残差补偿的人脸图像超分辨率算法[J]. 西安交通大学学报,2010,44(4):9-12.

MA Xiang, QI Chun. A face image super resolution algorithm based on global reconstruction and position patch residue compensation [J]. Journal of Xi'an Jiaotong University, 2010, 44(4):9-12.

WANG Zhou, BOVIK A C,SHEIKH H R,et al. Image quality assessment: from error visibility to structural similarity [J]. IEEE Transaction on Image Processing, 2004,13(4):600-612.

蒋舒卉,钱学明. 一种重要区域重采样的人脸检索方法. 2012,46(2):119-123.

穆为磊, 高建民, 陈富民,等. 符合人眼视觉特性的焊缝射线数字图像增强方法. 2012,46(3):90-93.

赵一博, 韩妙飞, 闫相国. 几种漫射光学成像图像重建算法的比较研究. 2012,46(4):106-111.

史金钢,齐春. 一种双约束稀疏模型图像修复算法. 2012,46(2):6-10.

吴攀超,王宗义,林欣堂. 采用局部差分模型描述的彩色图像配准技术. 2011,45(10):30-37.

徐胜军,韩九强,赵亮,等. 用于图像分割的局部区域能量最小化算法. 2011,45(8):7-12.

郝元宏,韩静,齐春. 一种新的浮选泡沫图像识别方法. 2011,45(4):104-108.

陈蓉,孙剑,徐宗本. 彩色图像分割中基于图上半监督学习算法研究. 2011,45(2):11-14.

杨艺,韩崇昭,韩德强. 利用特征子空间评价与多分类器融合的高光谱图像分类. 2010,44(8):20-24.

马祥,齐春. 全局重建和位置块残差补偿的人脸图像超分辨率算法. 2010,44(4):9-12.

温浩,郭崇慧. 利用粒子群优化的人脸特征提取识别算法. 2010,44(4):48-51.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Face Image Super-Resolution Algorithm Based on Global Reconstruction and Position-Patch Residue Compensation

A Selection Method of Projection Space for Face Super-Resolution Reconstruction

Polarization Image Super-Resolution Reconstruction Network Using Contextual Dual Self-Correlation Attention

A Greedy Layer-Wise Dictionary Training Algorithm Based on Genetic Approach

A Maximum Posteriori Super-Resolution Algorithm for Adaptive Estimation of Blur Parameter

Related Author

齐春

马祥

张哲 1

齐春 1

张钊强 1

陈晓璇 2

JIANG Hongyan

DUAN Jin

Related Institution

School of Electronic Information Engineering, Changchun University of Science and Technology

Changchun Genhius Technology Co., Ltd.

西安交通大学电子与信息工程学院

西安邮电学院通信与信息工程学院

National Key Laboratory of Integrated Service Networks, Xidian University

⁰