首页> 外国专利> DICTIONARY-TYPE IMAGE SUPER-RESOLUTION SYSTEM AND METHOD BASED ON ITERATION PROJECTION RECONSTRUCTION

DICTIONARY-TYPE IMAGE SUPER-RESOLUTION SYSTEM AND METHOD BASED ON ITERATION PROJECTION RECONSTRUCTION

机译：基于迭代投影重构的字典型图像超分辨率系统和方法

页面导航

摘要
著录项
相似文献

摘要

The present invention provides a dictionary-type image super-resolution system and method based on iteration projection reconstruction. The system comprises: a dictionary training and projection matrix pre-calculation module, a projection matrix-based iteration projection super-resolution reconstruction module, and a global restriction-based post-processing module. The method comprises: step S1, learning a dictionary, and calculating a projection matrix; step S2, projection matrix-based iteration projection super-resolution reconstruction: inputting y for a low-resolution image block, searching the dictionary for an atom most similar to y, performing super-resolution reconstruction on y by using a projection matrix of the atom, performing projection reconstruction on a generated residual vector again to obtain high-resolution reconstruction of the residual vector, performing iteration reconstruction in such a way, and finally, performing weighted addition on all reconstruction components, the sum serving as a final reconstruction resu and step S3, globally restricting a reconstructed image to eliminate an unnatural effect. The present invention can effectively increase the calculation speed of a dictionary-type method and can recover image high-frequency detail information.

机译：本发明提供了一种基于迭代投影重构的字典型图像超分辨率系统和方法。该系统包括：字典训练和投影矩阵预计算模块，基于投影矩阵的迭代投影超分辨率重建模块以及基于全局限制的后处理模块。该方法包括：步骤S1，学习词典，计算投影矩阵;步骤S2，基于投影矩阵的迭代投影超分辨率重建：输入 y 以获取低分辨率图像块，在字典中搜索与 y 最相似的原子，执行通过使用原子的投影矩阵对 y 进行超分辨率重建，再次对生成的残差矢量执行投影重建，以获得残差矢量的高分辨率重建，并以此方式进行迭代重建，最后，对所有重构分量进行加权加和，将其作为最终重构结果。步骤S3，全局限制重构图像以消除不自然的效果。本发明可以有效地提高字典型方法的计算速度，并且可以恢复图像高频细节信息。 展开▼

著录项

公开/公告号WO2017004890A1

专利类型

公开/公告日2017-01-12

原文格式PDF

申请/专利权人 PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOL;
展开▼

申请/专利号WO2015CN89307

发明设计人 ZHAO YANG;WANG RONGGANG;GAO WEN;WANG ZHENYU;WANG WENMIN;
展开▼

申请日2015-09-10

分类号G06T3;

国家 WO

入库时间 2022-08-21 13:33:04

相似文献

专利

外文文献

中文文献

1. 基于迭代投影重建的字典类图像超分辨率系统及方法 [P] . 中国专利： CN105023240B . 2019.07.09

2. 一种基于渐进式迭代反投影的图像超分辨率重建方法和系统 [P] . 中国专利： CN109544451A . 2019-03-29

3. Method for reconstructing image data based on projection data set, involves reconstructing start-image data based on projection data set with redundant projection data, where iterative reconstruction method is performed with iteration step [P] . 德国专利： DE102012209001A1 . 2014-01-02

机译：基于投影数据集重建图像数据的方法，包括基于具有冗余投影数据的投影数据集重建起始图像数据，其中迭代重建方法以迭代步骤执行

4. Method for iterative reconstruction of target image values in target area based on discrete target image elements described reconstruction data set of projection images, involves initializing unit of initializing data set [P] . 德国专利： DE102012200920A1 . 2013-07-25

机译：基于离散目标图像元素描述的投影图像重建数据集的目标区域中目标图像值的迭代重建方法，涉及初始化数据集的初始化单元

5. The apparatus for projection directly to perform a direct projection through an image reconstruction device to reconstruct iteratively a image of a region of interest from the projection data acquired, apparatus for acquisition of images to generate an image of a re GI of interest.Method of projecting directly to perform a direct projection by means of an image and computer program to perform a direct projection through an image [P] . BR112013012676A2 . 2016-08-23

机译：用于投影的设备通过图像重建设备直接执行直接投影以从获取的投影数据中迭代地重建关注区域的图像，该获取图像的设备生成感兴趣的re GI的图像。直接通过图像进行直接投影和计算机程序通过图像进行直接投影

1. Reconstruction of electrical capacitance tomography images based on fast linearized alternating direction method of multipliers for two-phase flow system [J] . Chongkun Xia, Chengli Su⁎, Jiangtao Cao, 中国化学工程学报（英文版） . 2016,第005期

2. Preconditioned Iterative Methods for Algebraic Systems from Multiplicative Half-Quadratic Regularization Image Restorations [J] . Zhong-Zhi, Yu-Mei, K. 高等学校计算数学学报：英文版 . 2010,第004期

3. Preconditioned Iterative Methods for Algebraic Systems from Multiplicative Half-Quadratic Regularization Image Restorations [J] . Zhong-Zhi Bai, Yu-Mei Huang, Michael K. Ng, 高等学校计算数学学报（英文版） . 2010,第004期

4. Enhanced Iterative Back-Projection Based Super-Resolution Reconstruction of Digital Images [J] . Nayak Rajashree, Patra Dipti Arabian Journal for Science and Engineering . 2018,第12期

5. Computed Tomography Image Quality Evaluation of a New Iterative Reconstruction Algorithm in the Abdomen (Adaptive Statistical Iterative Reconstruction-V) a Comparison With Model-Based Iterative Reconstruction, Adaptive Statistical Iterative Reconstruction, and Filtered Back Projection Reconstructions [J] . Goodenberger Martin H., Wagner-Bartak Nicolaus A., Gupta Shiva, Journal of computer assisted tomography . 2018,第2期

6. Low-light-level image super-resolution reconstruction based on iterative projection photon localization algorithm [J] . Ying Changsheng, Zhao Peng, Li Ye Journal of electronic imaging . 2018,第1期

7. Morphology based iterative back-projection for super-resolution reconstruction of image [C] . Nayak Rajashree, Harshavardhan Saka, Patra Dipti 2014 2nd International Conference on Emerging Technology Trends in Electronics, Communication and Networking . 2014

8. Development and Characterization of a Dither-Based Super-Resolution Reconstruction Method for Fiber Imaging Arrays [D] . Languirand, Eric Robert. 2017

9. Renal Cyst Pseudoenhancement: Intraindividual Comparison Between Virtual Monochromatic Spectral Images and Conventional Polychromatic 120-kVp Images Obtained During the Same CT Examination and Comparisons Among Images Reconstructed Using Filtered Back Projection Adaptive Statistical Iterative Reconstruction and Model-Based Iterative Reconstruction [O] . Yoshitake Yamada, Minoru Yamada, Koichi Sugisawa, -1

10. Computed Tomography Image Quality Evaluation of a New Iterative Reconstruction Algorithm in the Abdomen (Adaptive Statistical Iterative Reconstruction–V) a Comparison With Model-Based Iterative Reconstruction, Adaptive Statistical Iterative Reconstruction, and Filtered Back Projection Reconstructions [O] . Martin H. Goodenberger, Nicolaus A. Wagner-Bartak, Shiva Gupta, 2018

11. Iterative Methods for Sparse, Linear Systems Arising from Tomographic ImageReconstruction: The Relations Between ART, SIRT, and CG [R] . Vandijke, M. C. A., Viergever, M. A., Vandervorst, H. A. 1990

1. Super-Resolution image Reconstruction Based on Iteration and Wavelet Transform [J] . Wang Jing ,Aidi Wu . 通讯和计算机 . 2014,第001期

2. How to co-add images? I.A new iterative method for image reconstruction of dithered observations [J] . Lei Wang ,Guo-Liang Li . 天文和天体物理学研究 . 2017,第010期

3. 基于超分辨率重构的水面漂浮物动态图像识别报警系统 [C] . 胡文才 ,刘远征 . 沂沐泗第八届水文学术交流会 . 2017

4. 基于Lanczos插值的迭代反投影图像超分辨率算法 [A] . 杨琇卿 . 2018