DeepDeblur: text image recovery from blur to sharp

Digital images could be degraded by a variety of blur during the image acquisition (i.e. relative motion of cameras, electronic noise, capturing defocus, and so on). Blurring images can be computationally modeled as the result of a convolution process with the corresponding blur kernel and thus, image deblurring can be regarded as a deconvolution operation. In this paper, we explore to deblur images by approximating blind deconvolutions using a deep neural network. Different deep neural network structures are investigated to evaluate their deblurring capabilities, which contributes to the optimal design of a network architecture. It is found that shallow and narrow networks are not capable of handling complex motion blur. We thus, present a deep network with 20 layers to cope with text image blur. In addition, a novel network structure with Sequential Highway Connections (SHC) is leveraged to gain superior convergence. The experiment results demonstrate the state-of-the-art performance of the proposed framework with the higher visual quality of the delurred images.

[1]  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.

[2]  Ling Shao,et al.  Image Blur Classification and Parameter Identification Using Two-stage Deep Belief Networks , 2013, BMVC.

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

[4]  Ian D. Reid,et al.  From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[6]  Qi Tian,et al.  Enhancing Micro-video Understanding by Harnessing External Sounds , 2017, ACM Multimedia.

[7]  Jiri Matas,et al.  DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Ce Liu,et al.  Deep Convolutional Neural Network for Image Deconvolution , 2014, NIPS.

[9]  Meng Wang,et al.  Oracle in Image Search: A Content-Based Approach to Performance Prediction , 2012, TOIS.

[10]  Rob Fergus,et al.  Fast Image Deconvolution using Hyper-Laplacian Priors , 2009, NIPS.

[11]  Tae Hyun Kim,et al.  Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[13]  Meng Wang,et al.  Harvesting visual concepts for image search with complex queries , 2012, ACM Multimedia.

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

[15]  Sundaresh Ram,et al.  Removing Camera Shake from a Single Photograph , 2009 .

[16]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Giacomo Boracchi,et al.  Modeling the Performance of Image Restoration From Motion Blur , 2012, IEEE Transactions on Image Processing.

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

[19]  Jiaya Jia,et al.  High-quality motion deblurring from a single image , 2008, ACM Trans. Graph..

[20]  Frédo Durand,et al.  Understanding and evaluating blind deconvolution algorithms , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Ayan Chakrabarti,et al.  A Neural Approach to Blind Motion Deblurring , 2016, ECCV.

[22]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Jean Ponce,et al.  Learning a convolutional neural network for non-uniform motion blur removal , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[25]  Zhuowen Tu,et al.  Deeply-Supervised Nets , 2014, AISTATS.

[26]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[27]  Paramanand Chandramouli,et al.  Motion Deblurring in the Wild , 2017, GCPR.

[28]  Jiaya Jia,et al.  High-quality motion deblurring from a single image , 2008, SIGGRAPH 2008.

[29]  Giacomo Boracchi,et al.  Uniform Motion Blur in Poissonian Noise: Blur/Noise Tradeoff , 2011, IEEE Transactions on Image Processing.

[30]  Shubham Pachori,et al.  Deep Generative Filter for Motion Deblurring , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).