基于<i>L</i><sub>1/2</sub>自适应稀疏正则化的图像重建算法

叶向荣; 刘怡俊; 陈云华; 熊炯涛

doi:10.12052/gdutxb.170006

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于L_1/2自适应稀疏正则化的图像重建算法

综合研究 | 更新时间：2026-05-27

- 基于L_1/2自适应稀疏正则化的图像重建算法
- A Super-resolution Image Reconstruction Algorithm with Adaptive L_1/2 Sparse Regularization
- 广东工业大学学报 2017年34卷第6期页码：43-48
- 作者机构：
  
  1. 广东工业大学　计算机学院
  2. 广东工业大学　信息工程学院,广东,广州,510006
- 作者简介：
  
  叶向荣(1991–)，男，硕士研究生，研究方向为图像超分辨率重建和人脸识别. E-mail：121846283@qq.com
  刘怡俊(1977–)，男，教授，博士，研究方向为集成电路、北斗导航芯片与系统、计算机系统结构、物联网、嵌入式系统和信息管理系统. E-mail：yjliu@gdut.edu.cn
- 基金信息：
  
  广东省自然科学基金资助项目(2014A030310169，2016A030313713);广东省科技计划项目(2016B090918126，2016B090904001，2014B090901061，2015B090901060，2015B090908001，2015B090903080);广州市科技计划项目(2014Y2-00211)
- DOI：10.12052/gdutxb.170006
  中图分类号： TP391.41
- 网络首发：2017-11-09，
  
  纸质出版：2017
- 稿件说明：
移动端阅览
叶向荣, 刘怡俊, 陈云华, 熊炯涛. 基于L_1/2自适应稀疏正则化的图像重建算法[J]. 广东工业大学学报, 2017, 34(6): 43-48. DOI: 10.12052/gdutxb.170006.

Ye Xiang-rong, Liu Yi-jun, Chen Yun-hua, et al. A Super-resolution Image Reconstruction Algorithm with Adaptive L_1/2 Sparse Regularization[J]. 2017, 34(6): 43-48. DOI: 10.12052/gdutxb.170006.
叶向荣, 刘怡俊, 陈云华, 熊炯涛. 基于L_1/2自适应稀疏正则化的图像重建算法[J]. 广东工业大学学报, 2017, 34(6): 43-48. DOI: 10.12052/gdutxb.170006. DOI：

Ye Xiang-rong, Liu Yi-jun, Chen Yun-hua, et al. A Super-resolution Image Reconstruction Algorithm with Adaptive L_1/2 Sparse Regularization[J]. 2017, 34(6): 43-48. DOI: 10.12052/gdutxb.170006. DOI：

摘要

为了解决图像超分辨率重建过程中出现的问题

结合图像的稀疏表示

增加控制邻近块兼容性的约束

建立具有邻近块兼容性约束的

1/2

稀疏正则化模型. 采用加权

范式代替

1)范式

对迭代加权最小二乘法进行转化

提出一种自适应正则化参数选取的算法. 通过拼接字典的方法

训练出重要的特征并优化了重建图像的质量. 实验结果表明

该重建方法在去噪和保留边缘信息方面具有较好的效果

重建的高分辨率图像在视觉上具有清晰锐利的特点

而且在峰值信噪比和结构相似度两项指标上都优于传统的重建方法.

Abstract

In order to solve the ill-posing problem and poor effect of fixed regularization parameter in super-resolution image reconstruction

an adaptive regularization combining the study of sparse representation is proposed. By additional restrictions for compatibility of adjacent patches

a new

1/2

non-convex optimization model is built. Reweighted

Norm rather than

1) Norm is applied into the adaptive algorithm for adjustment of regularization parameter. With the help of joint dictionary training method

some impo

rtant features for improving the quality of reconstructed image are obtained. Experimental results show that the method has significant advantages in denoising and preserving edge details. It is showed that the proposed method not only makes the desired high-resolution images visually clearer

but it also outperforms some traditional methods in both the value of peak signal to noise ratio and structural similarity.

关键词

Keywords

references

TSAI R Y, HUANG T S. Multiframe image restoration and registration [M]. Greenwich: Advances in Computer Vision Image Processing, 1984: 317-339.

STARK H, OSKOUI P. High-resolution image recovery from image plane arrays, using convex project- tions [J]. Journal of the Optical Society of America, 1989, 6(11): 1715-1726.

SCHULZ R R, STEVENSON R L. Extraction of high- resolution frames from video sequences [J]. IEEE Trans, 1996, 5(6): 996-1011.

IRANI M, PELEG S. Improving resolution by image registration [J]. CVGIP: Graphical Models and Image Processing, 1991, 53(3): 231-239.

ZHANG X, LAM E Y, WU E X, et al . Application of Tikhonov regularization to super-resolution reconstruction of brain MRI image [J ] . Lecture Notes in Computer Science, 2008, 4987(23): 51-56.

RUDIN L, OSHER S, FATEMI E. Nonlinear total variation based on noise removal algorithm [J]. Physica D, 1992, 60: 259-268.

FARSIU S, ROBINSON M. Fast and robust multiframe super resolution [J]. IEEE Trans Image Process, 2004, 13(10): 1327-1344.

YANG J, WRIGHT J, HUANG T, et al. Image super- resolution as sparse representation of raw image patches [C]//IEEE Conference on Computer Vision and Pattern Recognition. [S. l.]: CVPR, 2008: 1-8.

YANG J, WRIGHT J, HUANG T S, et al . Image super-resolution via sparse representation [J ] . IEEE Trans Image Process, 2010, 19(11): 2861-2873.

ZHANG K, GAO X, TAO D, et al . Single image super- resolution with multiscale similarity learning [J ] . IEEE Trans Neural Networks and Learning Systems, 2013, 24(10): 1648-1659.

XU Z, ZHANG H, WANG Y, et al . L 1/2 regularization [J ] . Science China: Information Sciences, 2010, 53(6): 1159-1169.

HE X, NIYOGI P. Locality preserving project- tions [J]. Advances in Neural Information Pro- cessing Systems, 2002, 16(1): 186-197.

YU X, ZHANG S, ZHAO X, et al . Removing blur kernel noise via a hybrid lp norm [J ] . Electron Imaging, 2015, 1(24): 013011.

ZHANG Y, XU B, ZHOU S B, et al . Image super-resolution with adaptive regularization sparse representation [J ] . Application Research of Computers, 2013, 30(3): 938-941.

CAI T G, HUANG M H, LI C X, et al . Design of image acquisition and preprocessing of precise linear encoder based on FPGA [J ] . Journal of Guangdong University of Technology, 2016, 33(03): 60-64.

WANG H, WANG Y G. Super-resolution image reconstruction algorithm based on L 1/2 regularization [J ] . Computer Engineering, 2012, 38(20): 191-194.

CAO F L, CAI M M, TAN Y P, et al . Image super-resolution via adaptive (0 p 1) regularization and sparse representation [J ] . IEEE Trans Neural Networks and Lea rning Systems, 2016, 27(7): 1550-1561.

ZHONG X Y, XU S Q, DAI Z S. Detail based backlight image detection [J]. Journal of Guangdong University of Technology, 2016, 33(06): 72-76.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于多分辨率学习卷积神经网络的磁共振图像超分辨率重建

稀疏盲源分离问题的恢复性研究

盲稀疏源信号分离算法的恢复性研究

基于数字混频的脉冲式激光测距方法的研究与实现

基于PSI技术的福州市地面形变监测与影响因素分析

基于L1/2自适应稀疏正则化的图像重建算法

A Super-resolution Image Reconstruction Algorithm with Adaptive L1/2 Sparse Regularization

DOI：10.12052/gdutxb.170006

摘要

Abstract

关键词

Keywords

references

基于L_1/2自适应稀疏正则化的图像重建算法

A Super-resolution Image Reconstruction Algorithm with Adaptive L_1/2 Sparse Regularization