兰州大学机构库 >数学与统计学院
基于矩阵低秩化方法的图像去马赛克问题研究
Alternative TitleColor Image Demosaicing Based on Matrix Low-Rank Method
张旭
Subtype学士
Thesis Advisor黄玉梅
2017-05-16
Degree Grantor兰州大学
Place of Conferral兰州
Degree Name理学学士
Degree Discipline计算数学
Keyword矩阵低秩化 low-rank of matrix 图像去马赛克 color image demosaicing 加权核范数 weighted nuclear norm 交替迭代法 alternative iteration method
Abstract

彩色数码相机在记录彩色图像时,图像中每个像素三个颜色通道中的信息只有红色、蓝色或绿色被颜色滤波阵列采样,从而得到一个灰色图片,由这个灰色图片构造彩色图像的过程称为去马赛克过程。去马赛克方法的选择直接影响着彩色图像的色彩显示效果,色彩重构的效果是衡量去马赛克方法好坏的的主要依据。目前去马赛克的方法有内通道间的插值方法、合适插值方向的估计、图片非局部相似块的研究和解决反问题。

在本论文中,我们将研究利用矩阵低秩化方法进行图像的去马赛克,并考虑如何利用彩色图像不同通道信息的正则项,构造有效去除图像马赛克的模型并对其进行理论分析。然后设计求解该模型的算法,对算法进行理论分析。

Other Abstract

Most of the digital color cameras sample only one color value of red, green and blue channels at each pixel by color filter array, the obtained image is a gray image. The aim of demosaicing is to find efficient methods to get full color of the original image. The choice of the demosaicing method has a direct impact on the color display effect of color image, and the effect of color reconstruction is the main basis to measure the demosaicing method. There have been four ways proposed in the literature to complete demosaicing, they are interpolation between inter channels, the estimation of interpolation direction, nonlocal similarity patches of images and solving the inverse problem.

In this thesis, we focus on how to utilize low-rank image restoration method in demosaicing.  By using regularization term of different color image channel information,  we construct an efficient model for demosaicing and we also analyze the theoretical properties of the proposed model. Then we design algorithm for solving the model, and analysis astringency or other theoretical analysis.

MOST Discipline Catalogue计算数学
URL查看原文
Language中文
Other Code262010_320130926960
Document Type学位论文
Identifierhttps://ir.lzu.edu.cn/handle/262010/534962
Collection数学与统计学院
Affiliation
兰州大学数学与统计学院
Recommended Citation
GB/T 7714
张旭. 基于矩阵低秩化方法的图像去马赛克问题研究[D]. 兰州. 兰州大学,2017.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[张旭]'s Articles
Baidu academic
Similar articles in Baidu academic
[张旭]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[张旭]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.