元伟¹, 张立毅^1,2
AuthorsHTML:元伟¹, 张立毅^1,2
AuthorsListE:Yuan Wei¹, Zhang Liyi^1,2
AuthorsHTMLE:Yuan Wei¹, Zhang Liyi^1,2
Unit:1. 天津大学电子信息工程学院，天津 300072；2. 天津商业大学信息工程学院，天津 300134
Unit_EngLish:1．School of Electronic Information Engineering, Tianjin University, Tianjin 300072, China
2．School of Information Engineering, Tianjin University of Commerce, Tianjin 300134, China
Abstract_Chinese:为解决超分辨率图像盲复原问题, 研究了一种广义图像降质模型及广义超分辨率图像盲复原算法模型. 提出了基于TVBD的交替最小化超分辨率图像盲复原算法, 并加以改进以改善复原效果; 通过结合MSAA算法, 提出了基于TV交替最小化的快速中值超分辨率图像盲复原算法, 排除野值干扰, 提高算法精度和速度; 根据峰值信噪比和误差平方和, 提出两种新的客观评价指标, 衡量各算法的复原效果. 实验表明, 本文算法有效实现了超分辨率图像盲复原, 并提高了复原精度.
Abstract_English:In order to solve the problem in blind super resolution image reconstruction(BSRIR)，a novel general image degradation model and a general BSRIR model were studied. A BSRIR algorithm based on total variation blind deconvolution(TVBD)and alternating minimization(AM)was proposed and modified to improve the reconstruction. By combining MSAA with the algorithm mentioned above，a fast BSRIR algorithm based on TVBD and MSAA was proposed to remove the outlier effect and improve the speed and accuracy. According to peak signal to noise ratio(PSNR)and sum of square difference(SSD)，two novel objective quality metrics were proposed to assess the BSRIR algorithms. Experimental results confirm that the proposed algorithm can achieve higher accuracy in BSRIR.
Keyword_Chinese:超分辨率; 盲反卷积; 正则化; 交替最小化
Keywords_English:super resolution; blind deconvolution; regularization; alternating minimization

PDF全文下载地址:http://xbzrb.tju.edu.cn/#/digest?ArticleID=5787