Image Reconstruction Algorithm Based on Dictionary Update and Optimal Similarity Search

XU Jun

Chinese

您当前的位置：

首页 >

文章列表页 >

Image Reconstruction Algorithm Based on Dictionary Update and Optimal Similarity Search

更新时间：2026-09-04

- Image Reconstruction Algorithm Based on Dictionary Update and Optimal Similarity Search
- Vol. 34, Issue 2, Pages: 109-114(2017)
- 作者机构：
  
  1. 北京交通大学,北京,100044
  2. 万达信息股份有限公司,上海,201112
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2017
- 稿件说明：
移动端阅览
徐俊. 基于字典矩阵更新与最优相似度搜索的图像重构算法[J]. 微电子学与计算机, 2017, 34(2): 109-114, 118.

XU Jun. Image Reconstruction Algorithm Based on Dictionary Update and Optimal Similarity Search[J]. 2017, 34(2): 109-114.
徐俊. 基于字典矩阵更新与最优相似度搜索的图像重构算法[J]. 微电子学与计算机, 2017, 34(2): 109-114, 118. DOI：

XU Jun. Image Reconstruction Algorithm Based on Dictionary Update and Optimal Similarity Search[J]. 2017, 34(2): 109-114. DOI：

摘要

提出了基于字典矩阵更新与最优相似度搜索的图像重构算法.通过分析图像信号的稀疏表示

确定出目标信号与字典矩阵及系数向量的关系

并定义相似度搜索机制

以生成图像信息的字典矩阵; 通过估算相似度的线性组合最大值

在字典矩阵选取最优原子

从而确定其最优系数向量; 基于最优系数向量

计算纹理相似度

更新字典矩阵中的每一个原子

生成新的字典矩阵; 最后

对新的字典矩阵中的元素进行稀疏线性组合

对重构像素块进行拟合

通过最大化相似度值

获得目标块的重构

完成图像复原.实验结果显示: 在对大面积损坏图像重构时

此算法具有更好的重构质量

其输出图像的结构相似度更高

有效消除了模糊效应及纹理不连续效应

且拥有较高的重构效率.

Abstract

An image inpainting algorithm based on dictionary update and optimal similarity search was proposed in this paper. by analysis sparse representation of signals

to find the relationship between the target signal and the dictionary matrix and the coefficient vector

define SSIM index used to generate a dictionary matrix; then

the maximum value of linear combination approximation based on SSIM index is calculated

used to select the optimal atom in dictionary matrix

and calculate the optimal coefficient vector

use the optimal coefficient vector calculate the sum of the SSIM index to becomes the highest

and update each atom in dictionary matrix

to generate a new dictionary matrix; finally

the target patch is approximated by a sparse linear combination of the atoms of the new dictionary matrix using

introduce the SSIM index as the approximation performance

the optimal reconstruction results maximizing the SSIM index can be obtained

to complete the image inpainting. The experiment results showed that: this algorithm had better visual effect and structural similarity

reduce the blurring effect

and overcome the discontinuous texture effect in inpainting of images with large area damaged image.

关键词

Keywords

references

Papafitsoros K, Schönlieb C B. A combined first and second order variational approach for image Reconstruction[J]. Journal of Mathematical Imaging and Vision, 2014, 2 (48): 308-338. DOI: 308

Anamandra Sai Harees. Exemplar-based color image inpainting: A fractional gradient function approach[J]. Pattern Analysis and Applications, 2014, 2(17): 389-399. DOI: 389

Muhammad S, Irfan M, Baik Sung Wook. Sparse coded image super-resolution using K-SVD trained dictionary based on regularized orthogonal matching pursuit[J]. Bio-Medical Materials and Engineering, 2015, 1(26): 1399-1407. DOI: 1399

Kazi J N, Patil Y M. Comparative analysis of fragment based and exemplar based inpainting techniques[J]. International Journal of Advanced Research in Electrical, 2013, 3 (2): 1020-1026. DOI: 1020

Seyed Saeid Mirkamali, Nagabhushan P. Object removal by depth-wise image inpainting[J]. Signal, Image and Video Processing, 2015, 8(9): 1785-1794. DOI: 1785

曾令军. 基于压缩感知的射电天文图像重构[D]. 昆明: 昆明理工大学, 2014: 23-42.

Berntsson F, Baravdish G. Coefficient Identification in PDEs applied toimage inpainting[J]. Applied Mathematics and Computation, 2014, 242(11): 227-235. DOI: 227

Manya V Afonso, João M R Sanches. A total variation recursive space-variant filter for image denoising[J]. Elsevier Digital Signal Processing, 2015, 11(40): 101-116. DOI: 101

练秋生, 陈书贞, 孔令富. 基于双密度圆对称轮廓波二元分布模型的压缩传感图像重构[J]. 计算机学报, 2012, 35(8): 1774-1781. DOI: 1774

王晓红, 章婷. 一种基于视觉感兴趣区域的彩色图像增强方法[J]. 包装工程, 2014, 35(3): 84-88. DOI: 84

李俊柏, 黄文清, 黄牧. 改进的Criminisi图像修复算法[J]. 工业控制计算机, 2014, 7(27): 127-131. DOI: 127

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Implementation and verification of a dual-chain power gating strategy for low power design

Lightweight countermeasures against Spectre attacks on the branch prediction unit

Design of ultra-low power real-time clock circuits

Steganography model guided by attention mechanism and improved dense convolution

A review of large model development: technological evolution from BERT to Deepseek

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰