单帧图像超分辨中的自适应正则约束算法
|
摘要
单帧图像超分辨作为一个典型的欠定问题,在优化求解过程中需要引入正则项进行约束,以提高超分辨重建的稳定性。平滑性正则作为超分辨中的一种常用正则项,容易导致图像高频信息丢失,造成图像中的边缘部分模糊,影响重建图像的视觉效果。利用马尔科夫随机场(Markov Random Field,MRF)对局部图像进行建模,表征了局部图像块内像元间的相关关系,并基于此实现了超分辨过程中的自适应正则约束,有效避免了图像边缘等位置的模糊效应,提高了图像的重建性能。
As a typical undetermined problem,super-resolution of single-frame images needs to be constrained by regular terms in the process of optimization,so as to improve the stability of super-resolution reconstruction.As a regular term commonly used in super-resolution,smoothness regularities may lead to the loss of high frequency information in images,cause the blurring of marginal areas in images,and affect the visual effects of reconstructed images.Based on Markov random field(MRF),this paper built the model of local image,characterized the correlation between the pixels in the local image block and realized self-adapting regular constraint in the process of super-resolution,which can effectively avoid the blurring effect in the marginal areas and other positions in the images,and improve the performance of the image reconstruction.
As a typical undetermined problem,super-resolution of single-frame images needs to be constrained by regular terms in the process of optimization,so as to improve the stability of super-resolution reconstruction.As a regular term commonly used in super-resolution,smoothness regularities may lead to the loss of high frequency information in images,cause the blurring of marginal areas in images,and affect the visual effects of reconstructed images.Based on Markov random field(MRF),this paper built the model of local image,characterized the correlation between the pixels in the local image block and realized self-adapting regular constraint in the process of super-resolution,which can effectively avoid the blurring effect in the marginal areas and other positions in the images,and improve the performance of the image reconstruction.
引文
[1] CHANDRAN V,FOOKES C,LIN F,et al.Investigation into optical flow super-resolution for surveillance applications [C]//Proceedings of WDIC.2005:73-78.
[2] ZHANG L,ZHANG H,SHEN H,et al.A super-resolution reconstruction algorithm for surveillance images [J].Signal Processing,2010,90(3):848-859.
[3] GREENSPAN H,OZ G,KIRYATI N,et al.Super-resolution in MRI [C]//Proceeding of ISBI.2002:943-946.
[4] SHI W,CABALLERO J,LEDIG C,et al.Cardiac image super-resolution with global correspondence using multiatlas patchmatch [C]//Proceeding of MICCAI.2013:9-16.
[5] TRINH D,LUONG M,DIBOS F,et al.Novel example-based method for super-resolution and denoising of medical images [J].IEEE Transactions on Image Processing,2014,23(4):1882-1895.
[6] FATTAL R.Image upsampling via imposed edge statistics [J].ACM SIGGRAPH,2007,26(3):95.
[7] SUN J,XU Z,SHUM H Y.Image super-resolution using gra- dient profile prior [C]//Proceeding ofCVPR,2008:1-8.
[8] SUN J,XU Z,SHUM H Y.Gradient profile prior and its applications in image super-resolution and enhancement [J].IEEE Transactions on Image Processing,2011,20(6):1529-1542.
[9] NG M K,SHEN H,LAM E Y,et al.A total variation regularization based super-resolution reconstruction algorithm for digital video [J].EURASIP Journal on Advances in Signal Processing,2007,74585:1-16.
[10] ZHANG X,LAM E Y,WU E X,et al.Application of Tikhonov regularization to super-resolution reconstruction of brain MRI image[J].Lecture Notes in Computer Science,2008,4987:51-56.
[11] YUAN Q,ZHANG L,SHEN H.Multiframe super-resolution employing a spatially weighted total variation model [J].IEEE Transactions on Circuits System and Video Technology,2012,22(3):379-392.
[12] YANG C Y,YANG M H.Fast direct super-resolution by simple functions [C]//Proceeding of ICCV.2013:561-568.
[13] DONG C,CHEN C L,HE K,et al.Image super-resolution using deep convolutional networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(2):295-307.
[14] 代坤鹏.基于自相似性的自然图像超分辨重建[D].西安:西安电子科技大学,2013.
[15] 徐煜明,宋佳伟,肖贤建.基于亚像素块匹配和字典学习的超分辨率算法[J].计算机科学,2016,43(8):304-308.
[16] BABACAN S D,MOLINA R,KATSAGGELOS A K.Parameter estimation in tv image restoration using variational distribution approximation [J].IEEE Transactions on Image Processing,2008,17(3):326-339.
[17] FARSIU S,ROBINSON M D,ELAD M,et al.Fast and robust multi-frame superresolution [J].IEEE Transactions on Image Processing,2004,13(10):1327-1344.
[18] HUMBLOT F,MOHAMMAD-DJAFARI A.Super-Resolution Using Hidden Markov Model and Bayesian Detection Estimation Framework[J].Eurasip Journal on Advances in Signal Proces-sing,2006,2006(1):1-16.
[19] SUN J,SUN J,XU Z.Gradient profile prior and its applications in image super-resolution and enhancement[J].IEEE Transactions on Image Processing,2011,20(6):1529-1542.
[2] ZHANG L,ZHANG H,SHEN H,et al.A super-resolution reconstruction algorithm for surveillance images [J].Signal Processing,2010,90(3):848-859.
[3] GREENSPAN H,OZ G,KIRYATI N,et al.Super-resolution in MRI [C]//Proceeding of ISBI.2002:943-946.
[4] SHI W,CABALLERO J,LEDIG C,et al.Cardiac image super-resolution with global correspondence using multiatlas patchmatch [C]//Proceeding of MICCAI.2013:9-16.
[5] TRINH D,LUONG M,DIBOS F,et al.Novel example-based method for super-resolution and denoising of medical images [J].IEEE Transactions on Image Processing,2014,23(4):1882-1895.
[6] FATTAL R.Image upsampling via imposed edge statistics [J].ACM SIGGRAPH,2007,26(3):95.
[7] SUN J,XU Z,SHUM H Y.Image super-resolution using gra- dient profile prior [C]//Proceeding ofCVPR,2008:1-8.
[8] SUN J,XU Z,SHUM H Y.Gradient profile prior and its applications in image super-resolution and enhancement [J].IEEE Transactions on Image Processing,2011,20(6):1529-1542.
[9] NG M K,SHEN H,LAM E Y,et al.A total variation regularization based super-resolution reconstruction algorithm for digital video [J].EURASIP Journal on Advances in Signal Processing,2007,74585:1-16.
[10] ZHANG X,LAM E Y,WU E X,et al.Application of Tikhonov regularization to super-resolution reconstruction of brain MRI image[J].Lecture Notes in Computer Science,2008,4987:51-56.
[11] YUAN Q,ZHANG L,SHEN H.Multiframe super-resolution employing a spatially weighted total variation model [J].IEEE Transactions on Circuits System and Video Technology,2012,22(3):379-392.
[12] YANG C Y,YANG M H.Fast direct super-resolution by simple functions [C]//Proceeding of ICCV.2013:561-568.
[13] DONG C,CHEN C L,HE K,et al.Image super-resolution using deep convolutional networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(2):295-307.
[14] 代坤鹏.基于自相似性的自然图像超分辨重建[D].西安:西安电子科技大学,2013.
[15] 徐煜明,宋佳伟,肖贤建.基于亚像素块匹配和字典学习的超分辨率算法[J].计算机科学,2016,43(8):304-308.
[16] BABACAN S D,MOLINA R,KATSAGGELOS A K.Parameter estimation in tv image restoration using variational distribution approximation [J].IEEE Transactions on Image Processing,2008,17(3):326-339.
[17] FARSIU S,ROBINSON M D,ELAD M,et al.Fast and robust multi-frame superresolution [J].IEEE Transactions on Image Processing,2004,13(10):1327-1344.
[18] HUMBLOT F,MOHAMMAD-DJAFARI A.Super-Resolution Using Hidden Markov Model and Bayesian Detection Estimation Framework[J].Eurasip Journal on Advances in Signal Proces-sing,2006,2006(1):1-16.
[19] SUN J,SUN J,XU Z.Gradient profile prior and its applications in image super-resolution and enhancement[J].IEEE Transactions on Image Processing,2011,20(6):1529-1542.