Image motion blurring restoration of joint gradient prediction and guided filter
-
摘要:针对由相机与所摄景物之间发生相对位置移动所导致的图像运动模糊,提出了一种鲁棒的基于单幅运动模糊图像的盲反卷积算法。该方法首先通过预测图像中的较强边缘信息,实现用简单、易于求解的优化问题在傅里叶域中快速、准确地估计出点扩散函数。然后利用得到的点扩散函数,使用基于梯度约束的非盲反卷积算法复原清晰图像,同时采用一种新的边缘保持滤波器导引滤波来消除噪声并抑制振铃效应。实验结果表明:本文的算法能够快速地从单幅运动模糊图像复原出具有清晰边缘和纹理的高质量图像,并且运算时间不超过20 s。Abstract:To modify the image motion blurring induced by the relative position motion between a camera and a subject, a robust blind deconvolution method based on single image motion blurring was proposed. Firstly, the strong edges of a latent image was predicted. By constraining image gradient, the point spread function in frequency domain was estimated fast and robustly by this method. After that, the non-blind deconvolution algorithm based on the gradient constrain was used to restore the latent image. Meanwhile, a new edge preserving filter-guided filter was used to suppress the ringing and noise. Experiments show that the proposed method can restore a high quality image with clear edges and tissues from single motion blurring image, and the operation time is less than 20 s.
-
[1] 孙辉,李志强. 基于相位相关的匀速直线运动模糊图像位移参数估计[J]. 中国光学,2012,5(2):174-180. SUN H,LI ZH Q. Estimation of displacement parameters for uniform linearmotion-blurred images based on phase-only correlation[J].Chinese Optics,2012,5(2):174-180.(in Chinese) [2] KUNDUR D,HATZINAKOS D. Blind image deconvolution[J].IEEE Signal Processing Magazine,1996,13(3):43-64. [3] FERGUS R,SINGH B,HERTZMANN A,et al.. Removing camera shake from a single photograph[J].ACM Trans. on Graphics,2006(25):787-794. [4] SHAN Q,JIA J,AGARWALA A. High-quality motion deblurring from a single image[J].ACM Trans. on Graphics,2008,27(3):73-78. [5] LEVIN A,WEISS Y,DURAND F,et al.. Understanding blind deconvolution algorithms[J].IEEE Trans. Pattern Anal. and Mach. Intell.,2011,33(12):2354-2367. [6] JIA J. Single image motion deblurring using transparency[C]//IEEE Conf. on Computer Vision and Pattern Recognition,June 17-22,2007,Minneapolis,MN,2007. [7] 石明珠,许廷发,张坤. 运动成像混合模糊的全变分图像复原[J]. 光学 精密工程,2011,19(8):1973-1981. SHI M ZH,XU T F,ZHANG K. Total variation image restoration for mixed blur in moving image[J].Opt. Precision Eng.,2011,19(8),1973-1981.(in Chinese) [8] 冯亮,王平,许廷发,等. 运动模糊退化图像的双字典稀疏复原[J]. 光学 精密工程,2011,19(8):1982-1989. FENG L,WANG P,XU T F,et al.. Dual dictionary sparse restoration of blurred images[J].Opt. Precision Eng.,2011,19(8):1982-1989.(in Chinese) [9] JOSHI N,SZELISKI R,KRIEGMAN D J. Psf estimation using sharp edge prediction[C]//IEEE conf. on Computer Vision and Pattern Recognition,June 23-28,2008,Anchorage,AK,2008. [10] 温博,张启衡,张建林. 应用自解卷积和增量Wiener滤波实现迭代盲图像复原[J]. 光学 精密工程,2011,19(12):3049-3055. WEN B,ZHANG Q H,ZHANG J L. Realization of iterative blind image restoration by self deconvolution and increment Wiener filter[J].Opt. Precision Eng.,2011,19(12):3049-3055.(in Chinese) [11] 郭永彩,王婀娜,高潮. 空间自适应和正则化技术的盲图像复原[J]. 光学 精密工程,2008,16(11):2263-2267. GUO Y C,WANG E N,GAO CH. Blind image restoration algorithm based on space-adaptive and regularization[J].Opt. Precision Eng.,2008,16(11):2263-2267.(in Chinese) [12] 杨航. 图像反卷积算法研究[D].长春:吉林大学,2012. YANG H. Study on image deconvolution algorithm[D]. Changchun:Jilin University,2012(in Chinese). [13] YANG H,ZHANG ZH B. Fusion of wave atom-based wiener shrinkage filter and joint non-iocal means filter for texture-preserving image deconvolution[J].Opt. Eng.,2012,51(6):67-75. [14] HUANG H Y,YANG H,MA S L. Gradient based image deconvolution[J].J. Electronic Imaging,2013,22(1):013006. [15] HE K,SUN J,TANG X. Guided image filter[J].IEEE Trans. Pattern Anal. Mach. Intell.,2013,35(6):1397-1409.
点击查看大图
计量
- 文章访问数:2233
- HTML全文浏览量:185
- PDF下载量:603
- 被引次数:0