Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs

Photographs of text documents taken by hand-held cameras can be easily degraded by camera motion during exposure. In this paper, we propose a new method for blind deconvolution of document images. Observing that document images are usually dominated by small-scale high-order structures, we propose to learn a multi-scale, interleaved cascade of shrinkage fields model, which contains a series of high-order filters to facilitate joint recovery of blur kernel and latent image. With extensive experiments, we show that our method produces high quality results and is highly efficient at the same time, making it a practical choice for deblurring high resolution text images captured by modern mobile devices.

[1]  Jan Kotera,et al.  Convolutional Neural Networks for Direct Text Deblurring , 2015, BMVC.

[2]  Lei Zhang,et al.  Discriminative learning of iteration-wise priors for blind deconvolution , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Cong Phuoc Huynh,et al.  Class-Specific Image Deblurring , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[4]  Seungyong Lee,et al.  Text Image Deblurring Using Text-Specific Properties , 2012, ECCV.

[5]  Bernhard Schölkopf,et al.  Efficient filter flow for space-variant multiframe blind deconvolution , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Sebastian Nowozin,et al.  Interleaved Regression Tree Field Cascades for Blind Image Deconvolution , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[7]  Qionghai Dai,et al.  Hybrid Image Deblurring by Fusing Edge and Power Spectrum Information , 2014, ECCV.

[8]  Sunghyun Cho,et al.  Edge-based blur kernel estimation using patch priors , 2013, IEEE International Conference on Computational Photography (ICCP).

[9]  Donald Geman,et al.  Nonlinear image recovery with half-quadratic regularization , 1995, IEEE Trans. Image Process..

[10]  David A. Forsyth,et al.  Generalizing motion edits with Gaussian processes , 2009, ACM Trans. Graph..

[11]  Qiang Wu,et al.  An effective document image deblurring algorithm , 2011, CVPR 2011.

[12]  Sebastian Nowozin,et al.  Discriminative Non-blind Deblurring , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Ming-Hsuan Yang,et al.  Deblurring Text Images via L0-Regularized Intensity and Gradient Prior , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Bernhard Schölkopf,et al.  Learning to Deblur , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Wolfgang Heidrich,et al.  Stochastic Blind Motion Deblurring , 2015, IEEE Transactions on Image Processing.

[16]  Stefan Roth,et al.  Shrinkage Fields for Effective Image Restoration , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Li Xu,et al.  Unnatural L0 Sparse Representation for Natural Image Deblurring , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

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

[21]  Raanan Fattal,et al.  Blur-Kernel Estimation from Spectral Irregularities , 2012, ECCV.

[22]  Frédo Durand,et al.  Understanding and evaluating blind deconvolution algorithms , 2009, CVPR.

[23]  Michal Irani,et al.  Blind Deblurring Using Internal Patch Recurrence , 2014, ECCV.

[24]  Wei Yu,et al.  On learning optimized reaction diffusion processes for effective image restoration , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Michael J. Black,et al.  Fields of Experts: a framework for learning image priors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).