兰州大学机构库 >数学与统计学院
一种Retinex问题的加权总变分方法
Alternative TitleA Weighted Total Variational Method for Retinex
朱森林
Subtype硕士
Thesis Advisor黄玉梅
2018-03-31
Degree Grantor兰州大学
Place of Conferral兰州
Degree Name硕士
KeywordRetinex理论 光照图像 反射图像 加权总变分 交替迭代算法
Abstract

人类视觉系统在不同光照强度下对同一物体感知到的色彩是相同的, 这种现象被称为颜色恒常性理论. Retinex理论解释这一现象并表明人类视觉的色彩感知与光照强度无关,只与物体的内在反射属性有关. 基于Retinex理论,图像的灰度值是由两个因素决定的, 这两个因素分别是光照函数和反射函数. Retinex问题是要从一定光照强度下记录的图像中获取反应物体本身属性的反射值,从而获得物体的真实色彩.Retinex理论在图像增强、高动态范围图像色调映射、卫星图像纠正、目标跟踪、图像阴影消除等领域有着广泛的应用. 本文提出了解决Retinex问题的加权总变分模型,并设计了交替最小化迭代方法求解该模型. 实验结果表明利用本文构造的方法得到的反射图像和增强图像可以更好的保存图像纹理特征和边界信息.

Other Abstract

Human visual system can identify the constant color of a scene under varying illumination conditions which is called the color constancy theory. Retinex theory explains this phenomenon and shows that color sensations correlate with the intrinsic reflectance of an object and are independent of the illumination conditions. Based on the retinex theory, the pixel value of the image is determined by two factors. The two factors are the illumination function and the reflection function. The goal of retinex is to decompose the reflectance from a given image taken under a certain illumination and thereby obtaining the real color of the scene. The retinex theory is widely applied in image enhancement, high dynamic range image tonal mapping, satellite image correction, target tracking, image shadow elimination and so on. In this work, we propose a weighted total variational model for retinex problem. An alternating minimization algorithm is devised to solve the proposed model. The experimental results show that the reflectance and enhanced images obtained by weighted total variational model are much better in terms of both preservation.

URL查看原文
Language中文
Document Type学位论文
Identifierhttps://ir.lzu.edu.cn/handle/262010/224420
Collection数学与统计学院
Recommended Citation
GB/T 7714
朱森林. 一种Retinex问题的加权总变分方法[D]. 兰州. 兰州大学,2018.
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
[朱森林]'s Articles
Baidu academic
Similar articles in Baidu academic
[朱森林]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[朱森林]'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.