###
DOI:
Journal of Software:2007.18(10):2434-2444

基于广义Huber-MRF图像建模的超分辨率复原算法
邵文泽,韦志辉
(南京理工大学,计算机科学与技术学院,江苏,南京,210094)
Super-Resolution Reconstruction Based on Generalized Huber-MRF Image Modeling
SHAO Wen-Ze,WEI Zhi-Hui
()
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 3901   Download 3862
Received:July 17, 2005    Revised:June 30, 2006
> 中文摘要: 超分辨率图像复原是当今一个重要的热门研究课题.鉴于双边滤波优良的噪声抑制性和鲁棒的边缘保持性,提出一种双边滤波导出的广义MRF(Markov random field)图像先验模型.广义MRF模型不仅继承了双边滤波在阶数大邻域中的双重异性加权机制,且简洁地建立了双边滤波与Bayesian MAP(maximum a posterior)方法之间的理论联系.同时,由广义MRF模型导出了一种各向异性扩散PDE(partial differential equation)的改进数值解法.随后,在MRF-MAP框架下分别考虑高斯噪声和脉冲噪声两种情形,提出一种基于广义Huber-MRF模型的超分辨率复原算法,理论上保证具有严格全局最优解,并且利用半二次正则化思想和最速下降法求解相应的最小能量泛函.不论是视觉效果方面,还是峰值信噪比(PSNR)方面,实验结果都验证了广义Huber-MRF模型在超分辨图像复原中具有更强的噪声抑制性和边缘保持能力.
Abstract:Super-Resolution (SR) reconstruction has been a very hot research topic currently. A kind of generalized MRF (GMRF,generalized Markov random field) models is firstly proposed based on the recently reported bilateral filtering. The GMRF model is not only edge-preserving and robust to noise,inherited directly from the bilateral filtering,but also connects the bilateral filtering with the Bayesian MAP (maximum a posterior) approaches much concisely. Meanwhile,an improved numerical scheme of anisotropic diffusion PDE’s (partial differential equation) is deduced based on the GMRF model. In the MRF-MAP framework,a new SR restoration algorithm is subsequently proposed for both cases of Gaussian noise and impulse noise,utilizing the generalized Huber-MRF model which guarantees strictly global convergence. The half-quadratic regularization approach and steepest descent are exploited to solve the energy functional. Experimental results demonstrate the effectiveness of this approach,both in the visual effect and the PSNR value.
文章编号:     中图分类号:    文献标志码:
基金项目:Supported by the Key Science-Technology Project of Trigonal Yangtse River of China under Grant No.BE2004400 (长三角联合攻关重大科技项目); the National Natural Science Foundation of China under Grant No.60672074 (国家自然科学基金); the National High-Tech Research and Development Plan of China under Grant No.2007AA12E100 (国家高技术研究发展计划(863)); the National Research Foundation for the Doctoral Program of Higher Education of China under Grant No.M200606018 (国家教育部博士点基金); the Natural Science Foundation of Jiangsu Province of China under Grant No.BK2006569 (江苏省自然科学基金); the Science- Technology Creation Plan for Graduate Students of Jiangsu Province of China (江苏省高校研究生科技创新计划) Supported by the Key Science-Technology Project of Trigonal Yangtse River of China under Grant No.BE2004400 (长三角联合攻关重大科技项目); the National Natural Science Foundation of China under Grant No.60672074 (国家自然科学基金); the National High-Tech Research and Development Plan of China under Grant No.2007AA12E100 (国家高技术研究发展计划(863)); the National Research Foundation for the Doctoral Program of Higher Education of China under Grant No.M200606018 (国家教育部博士点基金); the Natural Science Foundation of Jiangsu Province of China under Grant No.BK2006569 (江苏省自然科学基金); the Science- Technology Creation Plan for Graduate Students of Jiangsu Province of China (江苏省高校研究生科技创新计划)
Foundation items:
Reference text:

邵文泽,韦志辉.基于广义Huber-MRF图像建模的超分辨率复原算法.软件学报,2007,18(10):2434-2444

SHAO Wen-Ze,WEI Zhi-Hui.Super-Resolution Reconstruction Based on Generalized Huber-MRF Image Modeling.Journal of Software,2007,18(10):2434-2444