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

您当前的位置：

首页 >

文章列表页 >

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

更新时间：2025-07-09

- A Face Image Super-Resolution Algorithm Based on Global Reconstruction and Position-Patch Residue Compensation
- Vol. 44, Issue 4, Pages: 9-12(2010)
- 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： TP391
- Online First：10 April 2010，
  
  Published：2010
- 稿件说明：
移动端阅览
A Face Image Super-Resolution Algorithm Based on Global Reconstruction and Position-Patch Residue Compensation[J]. 2010, 44(4): 9-12.
DOI：

A Face Image Super-Resolution Algorithm Based on Global Reconstruction and Position-Patch Residue Compensation[J]. 2010, 44(4): 9-12. DOI：

摘要

针对传统基于学习的人脸图像超分辨率算法存在高频细节信息损失过多问题

提出一种全局重建和位置块残差补偿相结合的人脸图像超分辨率新算法.首先利用高、低分辨率训练集所有样本

使用基于权值学习的全局重建算法得到初步的人脸图像

再结合图像模糊和下采样过程

产生高、低分辨率残差图像训练集

最后使用基于位置块的残差补偿算法

对初步的人脸图像进行高频细节补偿得到最终结果.对比实验结果表明

相比同类基于学习的人脸图像超分辨率算法

在将人脸图像分辨率提高4×4倍的情况下

新算法的平均峰值信噪比可提高0.65～3.55 dB

可以更好地重建出局部高频细节信息.

Abstract

Focusing on the high loss of subtle facial details in traditional algorithm

a face image super-resolution algorithm through global reconstruction and position-patch based residue compensation is presented. The optimal coefficients of the low-resolution training images are computed and transformed into high-resolution space to reconstruct the global high-resolution image. The residue training set is obtained by a smoothing and down-sampled processing. The residue compensation based on position is performed to better recover face subtle details using the residue training set. Experimental results show that the proposed approach synthesizes high-resolution faces with more details and the average of peak signal-to-noise ratios is improved about 0.65 dB to 3.55 dB compared with some existing learning-based methods.

关键词

Keywords

references

宋锐,贾嫒,吴成柯,等.自适应估计模糊参数的最大后验概率超分辨率复原算法[J].西安交通大学学报,2008, 42(10):1254-1258.

SONG Rui, JIA Yuan, WU Chengke, et al. A maximum posteriori super-resolution algorithm for adaptive estimation of blur parameter [J]. Journal of Xi'an Jiaotong University, 2008, 42(10):1254-1258.

WANG Xiaogang, TANG Xiaoou. Hallucinating face by eigentransformation [J]. IEEE Transactions on Systems Man and Cybernetics:Part C, 2005, 35(3): 425-434.

PARK J S, LEE S W. An example-based face hallucination method for single-frame, low-resolution facial images [J]. IEEE Transactions on Image Processing, 2008, 17(10): 1806-1816.

ZHUANG Yueting, ZHANG Jian, WU Fei. Hallucinating faces: LPH super-resolution and neighbor reconstruction for residue compensation [J]. Pattern Recognition, 2007, 40(11): 3178-3194.

ROWEIS S T, SAUL L K. Nonlinear dimensionality reduction by locally linear embedding [J]. Science, 2000, 22(12): 2323-2326.

SAUL L K. An Introduction to Locally Linear Embedding [EB/OL].(2001-01-01)[2008-04-05]. http:∥www.cs.toronto.edu/～roweis/lle/publications.html.

LIU Ce, SHUM H Y, ZHANG C S. A two-step approach to hallucinating faces: global parametric model and local nonparametric model [C]∥Proceeding of the Inter Conference on Image and Graphics.Piscataway, NJ, USA: IEEE, 2001: 192-198.

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.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

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

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

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

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

Multi-Scale Regional Attention InfoGAN License Plate Recognition Network

Related Author

李玉花

齐春

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.

National Key Laboratory of Integrated Service Networks, Xidian University

西安建筑科技大学信息与控制工程学院

西安市建筑制造智动化技术重点实验室

⁰