离焦模糊图像复原技术综述
|
摘要
数字图像复原是将已经退化的图像恢复到退化前的原始图像,用来获取自己需要的信息。近年来,图像复原技术虽然得到了广泛的研究,但是依然存在一些问题,有些算法需要做些改进。先介绍了图像复原技术,了解该技术的数学背景;然后介绍了离焦模糊图像的成因以及光学模型对现阶段广泛应用的离焦模糊图像的复原技术进行了概述,并指出了它们在应用时所存在的问题;最后总结了近几年大家在应用这些算法时所做的改进。
Digital image restoration is the restoration of degraded image to the original image before degradation,in order to obtain the information from images. In recent years,although image restoration technology has been widely studied,there are still some problems and algorithms required improvements. The article first describes the recovery technology and the mathematical background of image restoration technology. Then,we showthe causes of defocusing and an optical model of the defocused image. We also describe reviewthe defocusing image restoration techniques that are widely used at this stage and pointed out their limitations in the application. Finally,we summarize the improvements we have made in applying these algorithms in recent years.
Digital image restoration is the restoration of degraded image to the original image before degradation,in order to obtain the information from images. In recent years,although image restoration technology has been widely studied,there are still some problems and algorithms required improvements. The article first describes the recovery technology and the mathematical background of image restoration technology. Then,we showthe causes of defocusing and an optical model of the defocused image. We also describe reviewthe defocusing image restoration techniques that are widely used at this stage and pointed out their limitations in the application. Finally,we summarize the improvements we have made in applying these algorithms in recent years.
引文
[1] R. Fergus et al. Removing camera shakefrom a single photograph[J]. ACM Trans. Graphics 2006,25(3):787-794.
[2]杨彦.图像复原算法[D].成都:四川大学,2004.
[3] HUEI-YUNG LIN,KAI-DA GU. Depth Recovery Using Defocus Blur at Infinity[J]. IEEE,2008.
[4]姚敏.数字图像处理[M].北京:机械工业出版社,2006.
[5]胡学龙,许开宇.数字图像处理[M].北京:电子工业出版社,2006.
[6]邹谋炎.反卷积和信号复原[M].北京:国防工业出版社,2001:184-214.
[7]冈萨雷斯(Gonzalez R. C).数字图像处理(第二版)(英文版)[M].北京:电子工业出版社,2002:220-281.
[8] HOCK LIM,KAH-CHYE TAN,B T G TAN. Edge errors in inverse and w iener filter restorations of motion-blurred images and their w indow ing treatment[J]. CVGIP,1991,17(53):186-195.
[9]孙辉.离焦模糊图像的维纳滤波恢复[D].北京:中国科学院,2009.
[10]魏文力,李宝树,崔克彬,等.基于改进的最大熵航拍输电线路图像复原方法[J].科学技术与工程,2013,13(32):9701-9706.
[11]HANSEN PC,O’LEARY DP. The use of the L-curve in the regularization of discrete ill posed problems[J]. SIAM Journal on Scientific Computing,1993,14(7):1487-1503.
[12]俞梅,周宗玉.约束的最小二乘方图像复原方法的改进[J].信号处理,2000,16(2):177-179
[13]TEKALP A,KAUFMAN H,WOODS J. Edge-Adaptive Kalman filtering for image restoration w ith ringing suppression[J]. IEEE Transactions on Acoustic Speech and Signal Processing,1989,37(6):892-899.
[14]曾三友,康立山.一种基于正则化方法的准最佳图像复原技术[J].软件学报,2003,20(3):689-696
[15]刘晓辉,郭成安,胡家升.惯性约束聚变中环孔编码图像恢复的改进维纳滤波方法[J].光子学报,2004,24(8):1045-1050.
[16]韩小芳.运动与离焦模糊图像复原[D].大连:大连理工大学,2011.
[17]胡小平.离焦模糊图像的维纳滤波复原研究[J].仪器仪表学报,2007,28(3):480-482.
[18]王媛媛.离焦模糊图像处理的研究与应用[D].北京:北方工业大学,2011.
[19]辛玲.基于维纳滤波模糊图像复原算法的改进[J].硅谷,2012,5(23):178-179.
[20]梁晓萍,罗晓曙.基于遗传自适应的维纳滤波图像去模糊算法[J].广西师范大学学报(自然科学版),2017,35(4):17-23.
[21]KAI-SVEN M,FIKRET K,STEFAN R,et al. Genetic algorithms:concepts and designs[J]. Assembly Automation,1999,4(1):826-835.
[22]杜苗苗,杨灿美.一种维纳滤波图像复原算法的k值快速估计[J].微电子学与计算机,2015,32(8):46-53.
[23]张晓军.单幅模糊图像复原技术的研究与实现[D].西安:西北工业大学,2014.
[24]许尚文.非凸性高阶全变差正则化盲图像复原方法研究[D].重庆:重庆大学,2015.
[25]陈新平.共焦显微图像复原及其正则化方法研究[D].重庆:重庆理工大学,2011.
[26]曲荣召.基于点扩散函数估计的正则化图像复原方法[D].哈尔滨:哈尔滨工业大学,2016.
[27]赵晓伟.基于稀疏约束正则化的图像复原算法[D].秦皇岛:燕山大学,2014.
[28]田玉针.基于全变差正则化的图像复原[D].天津:天津大学,2015.
[29]刘巧红.基于正则化方法的图像复原算法研究[D].上海:上海大学,2015.
[30]苗晴.图像复原中正则化方法的研究及应用[D].北京:国防科技大学,2005.
[31]林新潜.正则化图像复原中的自适应方法研究与实现[D].哈尔滨:哈尔滨工业大学,2013.
[32]吴清平.正则化自适应平滑约束图像复原算法[J].福建电脑,2018,2(2):4-6.
[33]高源.正则化最小二乘结合偏微分方程的图像复原技术研究[D].哈尔滨:哈尔滨理工大学,2010.
[34]YU-LI Y,KAVEH M. Fourth-order partial differential equations for noise removal[J]. IEEE Trans Image Processing,2000,17(9):1723-1730.
[35]WU YD,CHEN YH,ZHANG HY. An improved algorithm for image restoration based on modified hopfield neural netw ork[J]. M achine Learning and Cybernetics. 2005,48(7):4720-4723.
[36]SUN Y. Hopfield neural network based algorithms for image restoration and reconstruction II. Performance analysis[J]. IEEE Transactions on Signal Processing2000,8(7):2119-2131.
[37]石晓玲.基于卷积神经网络的交通监控模糊图像复原技术[J].智能城市,2017,3(01):147-149.
[38]兰妙萍.基于卷积神经网络的图像复原方法研究[D].无锡:江南大学,2017.
[39]WANG D H,TALEVSKI A,DILLON T S. Edge-preserving nonlinear image restoration using adaptive components-based radial basis function neural netw orks[A]. In Proceeding of the International Joint Conference on Netw orks[C]. Portland,OR,USA,2003,2:1243-1248.
[40]张维.基于神经网络的图像复原方法研究[D].昆明:昆明理工大学,2017.
[41]董琪琪.彩色滤波阵列插值及图像复原算法研究[D].北京:中国科学院大学,2016.
[42] FUNG Y H,CHAN Y H. An iterative algorithm for restoring color-quantized images[J]. Image Processing,2002,1(3):313-316.
[43]FUNG Y H,CHAN Y H. POCS-based algorithm for restoring color-quantized images[J]. IEE Vision Image Signal Processing,2004,151(2):119-127.
[44]FUNG Y H,CHAN Y H. Restoration of halftoned color-quantized images using projection onto conves sets[J]. Image processing,2004,1(1):325-328.
[45]FUNG Y H,CHAN Y H. POCS-based restoration algorithm for restoring halftoned color-quantized images[J]. IEE Vision Image Signal Processing,2006,15(7):1985-1992.
[46]STANLEY J,REEVES. Fast image restoration without boundary artifacts[J]. IEEE Transactions on Image processing,2005,14(10):1448-1453.
[47]MARIO A. T. FIGUEIREDO,ROBERT D. NOWAK.An EM algorithm for w avelet based image restoration[J]. IEEE Transactions on Image Processing,2003,12(8):906-916.
[48]MICHAEL E,ZERVAKIS,TAEK MU. KWON et al.M ultiresolultion image restoration in the w avelet domain. ieee transactions on circuits and systems-H[J].Analog and Digital Signal Processing,1995,42(9):578-591.
[49]LIN T C. YUPT. Adaptive two-pass median filter based on support vector[J]. M achines for Image Restoration Neural Computation. 2004,16(2):333-354.
[2]杨彦.图像复原算法[D].成都:四川大学,2004.
[3] HUEI-YUNG LIN,KAI-DA GU. Depth Recovery Using Defocus Blur at Infinity[J]. IEEE,2008.
[4]姚敏.数字图像处理[M].北京:机械工业出版社,2006.
[5]胡学龙,许开宇.数字图像处理[M].北京:电子工业出版社,2006.
[6]邹谋炎.反卷积和信号复原[M].北京:国防工业出版社,2001:184-214.
[7]冈萨雷斯(Gonzalez R. C).数字图像处理(第二版)(英文版)[M].北京:电子工业出版社,2002:220-281.
[8] HOCK LIM,KAH-CHYE TAN,B T G TAN. Edge errors in inverse and w iener filter restorations of motion-blurred images and their w indow ing treatment[J]. CVGIP,1991,17(53):186-195.
[9]孙辉.离焦模糊图像的维纳滤波恢复[D].北京:中国科学院,2009.
[10]魏文力,李宝树,崔克彬,等.基于改进的最大熵航拍输电线路图像复原方法[J].科学技术与工程,2013,13(32):9701-9706.
[11]HANSEN PC,O’LEARY DP. The use of the L-curve in the regularization of discrete ill posed problems[J]. SIAM Journal on Scientific Computing,1993,14(7):1487-1503.
[12]俞梅,周宗玉.约束的最小二乘方图像复原方法的改进[J].信号处理,2000,16(2):177-179
[13]TEKALP A,KAUFMAN H,WOODS J. Edge-Adaptive Kalman filtering for image restoration w ith ringing suppression[J]. IEEE Transactions on Acoustic Speech and Signal Processing,1989,37(6):892-899.
[14]曾三友,康立山.一种基于正则化方法的准最佳图像复原技术[J].软件学报,2003,20(3):689-696
[15]刘晓辉,郭成安,胡家升.惯性约束聚变中环孔编码图像恢复的改进维纳滤波方法[J].光子学报,2004,24(8):1045-1050.
[16]韩小芳.运动与离焦模糊图像复原[D].大连:大连理工大学,2011.
[17]胡小平.离焦模糊图像的维纳滤波复原研究[J].仪器仪表学报,2007,28(3):480-482.
[18]王媛媛.离焦模糊图像处理的研究与应用[D].北京:北方工业大学,2011.
[19]辛玲.基于维纳滤波模糊图像复原算法的改进[J].硅谷,2012,5(23):178-179.
[20]梁晓萍,罗晓曙.基于遗传自适应的维纳滤波图像去模糊算法[J].广西师范大学学报(自然科学版),2017,35(4):17-23.
[21]KAI-SVEN M,FIKRET K,STEFAN R,et al. Genetic algorithms:concepts and designs[J]. Assembly Automation,1999,4(1):826-835.
[22]杜苗苗,杨灿美.一种维纳滤波图像复原算法的k值快速估计[J].微电子学与计算机,2015,32(8):46-53.
[23]张晓军.单幅模糊图像复原技术的研究与实现[D].西安:西北工业大学,2014.
[24]许尚文.非凸性高阶全变差正则化盲图像复原方法研究[D].重庆:重庆大学,2015.
[25]陈新平.共焦显微图像复原及其正则化方法研究[D].重庆:重庆理工大学,2011.
[26]曲荣召.基于点扩散函数估计的正则化图像复原方法[D].哈尔滨:哈尔滨工业大学,2016.
[27]赵晓伟.基于稀疏约束正则化的图像复原算法[D].秦皇岛:燕山大学,2014.
[28]田玉针.基于全变差正则化的图像复原[D].天津:天津大学,2015.
[29]刘巧红.基于正则化方法的图像复原算法研究[D].上海:上海大学,2015.
[30]苗晴.图像复原中正则化方法的研究及应用[D].北京:国防科技大学,2005.
[31]林新潜.正则化图像复原中的自适应方法研究与实现[D].哈尔滨:哈尔滨工业大学,2013.
[32]吴清平.正则化自适应平滑约束图像复原算法[J].福建电脑,2018,2(2):4-6.
[33]高源.正则化最小二乘结合偏微分方程的图像复原技术研究[D].哈尔滨:哈尔滨理工大学,2010.
[34]YU-LI Y,KAVEH M. Fourth-order partial differential equations for noise removal[J]. IEEE Trans Image Processing,2000,17(9):1723-1730.
[35]WU YD,CHEN YH,ZHANG HY. An improved algorithm for image restoration based on modified hopfield neural netw ork[J]. M achine Learning and Cybernetics. 2005,48(7):4720-4723.
[36]SUN Y. Hopfield neural network based algorithms for image restoration and reconstruction II. Performance analysis[J]. IEEE Transactions on Signal Processing2000,8(7):2119-2131.
[37]石晓玲.基于卷积神经网络的交通监控模糊图像复原技术[J].智能城市,2017,3(01):147-149.
[38]兰妙萍.基于卷积神经网络的图像复原方法研究[D].无锡:江南大学,2017.
[39]WANG D H,TALEVSKI A,DILLON T S. Edge-preserving nonlinear image restoration using adaptive components-based radial basis function neural netw orks[A]. In Proceeding of the International Joint Conference on Netw orks[C]. Portland,OR,USA,2003,2:1243-1248.
[40]张维.基于神经网络的图像复原方法研究[D].昆明:昆明理工大学,2017.
[41]董琪琪.彩色滤波阵列插值及图像复原算法研究[D].北京:中国科学院大学,2016.
[42] FUNG Y H,CHAN Y H. An iterative algorithm for restoring color-quantized images[J]. Image Processing,2002,1(3):313-316.
[43]FUNG Y H,CHAN Y H. POCS-based algorithm for restoring color-quantized images[J]. IEE Vision Image Signal Processing,2004,151(2):119-127.
[44]FUNG Y H,CHAN Y H. Restoration of halftoned color-quantized images using projection onto conves sets[J]. Image processing,2004,1(1):325-328.
[45]FUNG Y H,CHAN Y H. POCS-based restoration algorithm for restoring halftoned color-quantized images[J]. IEE Vision Image Signal Processing,2006,15(7):1985-1992.
[46]STANLEY J,REEVES. Fast image restoration without boundary artifacts[J]. IEEE Transactions on Image processing,2005,14(10):1448-1453.
[47]MARIO A. T. FIGUEIREDO,ROBERT D. NOWAK.An EM algorithm for w avelet based image restoration[J]. IEEE Transactions on Image Processing,2003,12(8):906-916.
[48]MICHAEL E,ZERVAKIS,TAEK MU. KWON et al.M ultiresolultion image restoration in the w avelet domain. ieee transactions on circuits and systems-H[J].Analog and Digital Signal Processing,1995,42(9):578-591.
[49]LIN T C. YUPT. Adaptive two-pass median filter based on support vector[J]. M achines for Image Restoration Neural Computation. 2004,16(2):333-354.