Kernel Optimization for Blind Motion Deblurring with Image Edge Prior

Image motion deblurring with unknown blur kernel is an ill-posed problem. This paper proposes a blind motion deblurring approach that solves blur kernel and the latent image robustly. For kernel optimization, an edge mask is used as an image prior to improve kernel update, then an edge selection mask is adopted to improve image update. In addition, an alternative iterative method is introduced to perform kernel optimization under a multiscale scheme. Moreover, for image restoration, a total-variation-(TV-) based algorithm is proposed to recover the latent image via nonblind deconvolution. Experimental results demonstrate that our method obtains accurate blur kernel and achieves better deblurring results than previous works.

[1]  Frédo Durand,et al.  Image and depth from a conventional camera with a coded aperture , 2007, SIGGRAPH 2007.

[2]  Wotao Yin,et al.  An Iterative Regularization Method for Total Variation-Based Image Restoration , 2005, Multiscale Model. Simul..

[3]  C. Cattani,et al.  Markov Models for Image Labeling , 2012 .

[4]  Curtis R. Vogel,et al.  Ieee Transactions on Image Processing Fast, Robust Total Variation{based Reconstruction of Noisy, Blurred Images , 2022 .

[5]  Tzu-Heng Henry Lee.  Edge Detection Analysis , 2007 .

[6]  Pong C. Yuen,et al.  Kernel machine-based rank-lifting regularized discriminant analysis method for face recognition , 2011, Neurocomputing.

[7]  Sunghyun Cho,et al.  Fast motion deblurring , 2009, SIGGRAPH 2009.

[8]  Shree K. Nayar,et al.  Motion-based motion deblurring , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Jianwei Zhang,et al.  A Hierarchical Model Incorporating Segmented Regions and Pixel Descriptors for Video Background Subtraction , 2012, IEEE Transactions on Industrial Informatics.

[10]  Y F Li,et al.  Determination of Stripe Edge Blurring for Depth Sensing , 2011, IEEE Sensors Journal.

[11]  Tom Goldstein,et al.  The Split Bregman Method for L1-Regularized Problems , 2009, SIAM J. Imaging Sci..

[12]  Stanley Osher,et al.  Total variation based image restoration with free local constraints , 1994, Proceedings of 1st International Conference on Image Processing.

[13]  Wen-Sheng Chen,et al.  Robust Affine Invariant Descriptors , 2011 .

[14]  Richard Szeliski,et al.  PSF estimation using sharp edge prediction , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  William T. Freeman,et al.  Removing camera shake from a single photograph , 2006, SIGGRAPH 2006.

[16]  Qionghai Dai,et al.  Exploring aligned complementary image pair for blind motion deblurring , 2011, CVPR 2011.

[17]  Zhongjie Wang,et al.  Improved Generalized Belief Propagation for Vision Processing , 2011 .

[18]  Deepa Kundur,et al.  Blind Image Deconvolution , 2001 .

[19]  Junfeng Yang,et al.  A New Alternating Minimization Algorithm for Total Variation Image Reconstruction , 2008, SIAM J. Imaging Sci..

[20]  Ming Li,et al.  Noise Estimation for Single-Slice Sinogram of Low-Dose X-Ray Computed Tomography Using Homogenous Patch , 2012 .

[21]  Ming Li,et al.  Representation of a Stochastic Traffic Bound , 2010, IEEE Transactions on Parallel and Distributed Systems.

[22]  Wang Jing.  Total Variant Image Deblurring Based on Split Bregman Method , 2012 .

[23]  Rob Fergus,et al.  Blind deconvolution using a normalized sparsity measure , 2011, CVPR 2011.

[24]  Ming Li,et al.  Viewing Sea Level by a One-Dimensional Random Function with Long Memory , 2011 .

[25]  Jian-Feng Cai,et al.  Blind motion deblurring from a single image using sparse approximation , 2009, CVPR.

[26]  Shmuel Peleg,et al.  Two motion-blurred images are better than one , 2005, Pattern Recognit. Lett..

[27]  José M. Bioucas-Dias,et al.  Fast Image Recovery Using Variable Splitting and Constrained Optimization , 2009, IEEE Transactions on Image Processing.

[28]  Xiaoli Li,et al.  The Specular Exponent as a Criterion for Appearance Quality Assessment of Pearllike Objects by Artificial Vision , 2012, IEEE Transactions on Industrial Electronics.

[29]  Tomaso A. Poggio,et al.  On Edge Detection , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Li Xu,et al.  Two-Phase Kernel Estimation for Robust Motion Deblurring , 2010, ECCV.

[31]  Jiaya Jia,et al.  Single Image Motion Deblurring Using Transparency , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Truong Q. Nguyen,et al.  An Augmented Lagrangian Method for Total Variation Video Restoration , 2011, IEEE Transactions on Image Processing.