CNN for license plate motion deblurring

In this work we explore the previously proposed approach of direct blind deconvolution and denoising with convolutional neural networks (CNN) in a situation where the blur kernels are partially constrained. We focus on blurred images from a real-life traffic surveillance system, on which we, for the first time, demonstrate that neural networks trained on artificial data provide superior reconstruction quality on real images compared to traditional blind deconvolution methods. The training data is easy to obtain by blurring sharp photos from a target system with a very rough approximation of the expected blur kernels, thereby allowing custom CNNs to be trained for a specific application (image content and blur range). Additionally, we evaluate the behavior and limits of the CNNs with respect to blur direction range and length.

[1]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Bernhard Schölkopf,et al.  A Machine Learning Approach for Non-blind Image Deconvolution , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  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.

[4]  Frédo Durand,et al.  Understanding Blind Deconvolution Algorithms , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Seungyong Lee,et al.  Handling outliers in non-blind image deconvolution , 2011, 2011 International Conference on Computer Vision.

[6]  Pei-Lun Hsieh,et al.  Recognition of blurred license plate images , 2010, 2010 IEEE International Workshop on Information Forensics and Security.

[7]  Yong Zhao,et al.  Licence plate images deblurring with binarization threshold , 2015, 2015 IEEE International Conference on Imaging Systems and Techniques (IST).

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

[9]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[10]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

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

[12]  Jean Ponce,et al.  Non-uniform Deblurring for Shaken Images , 2012, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[14]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[15]  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).

[16]  Rob Fergus,et al.  Restoring an Image Taken through a Window Covered with Dirt or Rain , 2013, 2013 IEEE International Conference on Computer Vision.

[17]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Jean Ponce,et al.  Non-uniform Deblurring for Shaken Images , 2010, International Journal of Computer Vision.

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

[20]  Chunhe Song,et al.  Blurred License Plate Recognition based on single snapshot from drive recorder , 2015, 2015 IEEE International Conference on Communications (ICC).

[21]  H. Sebastian Seung,et al.  Natural Image Denoising with Convolutional Networks , 2008, NIPS.

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