Text Deblurring Using OCR Word Confidence

Full Text (PDF, 434KB), PP.33-40

Views: 0 Downloads: 0

Author(s)

Avinash Verma 1,* Deepak Kumar Singh 2

1. BBD University Lucknow, India

2. Integral University Lucknow, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2017.01.05

Received: 14 Sep. 2016 / Revised: 20 Oct. 2016 / Accepted: 23 Nov. 2016 / Published: 8 Jan. 2017

Index Terms

Deblurring, Point Spread Function, Optical Character Recognition, Motion blur and Blind deconvolution

Abstract

Objective of this paper is to propose a new Deblurring method for motion blurred textual images. This technique is based on estimating the blur kernel or the Point Spread Function of the motion blur using Blind Deconvolution method. Motion blur is either due to the movement of the camera or the object at the time of image capture. The point spread function of the motion blur is governed by two parameters length of the motion and the angle of the motion. In this approach we have estimated point spread function for the motion blur iteratively for different values of the length and angle of motion. For every estimated PSF we perform the Deconvolution operation with the blurred image to get the non- blurred or the latent image. Latent image obtained is then feed to an Optical character recognition so that the text in that image can be recognized. Then we calculate the Average Word Confidence for the recognized text. Thus for every estimated Point Spread Function and the obtained latent image we get the value of Average Word Confidence. The Point Spread Function with the highest Average Word Confidence value is the optimal Point Spread Function which can be used to deblur the given textual image. In this method we do not have any prior information about the PSF and only single image is used as an input to the system. This method has been tested with the naturally blurred image taken manually and through the internet as well as artificially blurred image for the evaluation of the results. The implementation of the proposed algorithm has been done in MATLAB. 

Cite This Paper

Avinash Verma, Deepak Kumar Singh,"Text Deblurring Using OCR Word Confidence", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.9, No.1, pp.33-40, 2017. DOI: 10.5815/ijigsp.2017.01.05

Reference

[1]Taeg Sang Cho,Sylvain Paris,Berthold K. P. Horn,William T. Freeman "Blur Kernel Estimation using the Radon Transform" Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on June 2011.

[2]Shamik Tiwari, V. P. Shukla, and A. K. Singh "Review of Motion Blur Estimation Techniques" Journal of Image and Graphics Vol. 1, No. 4, December 2013.

[3]Kishore R. Bhagat,Puran Gour "Novel Approach to Estimate Motion Blur Kernel Parameters and Comparative Study of Restoration Techniques"International Journal of Computer Applications (0975 – 8887) Volume 72– No.17, June 2013.

[4]Lu Fang, Haifeng Liu, Feng Wu, Xiaoyan Sun, Houqiang Li "Separable Kernel for Image Deblurring" 2014 IEEE Conference on Computer Vision and Pattern Recognition Pages: 2885 - 2892, DOI: 10.1109/CVPR.2014.369.

[5]Nimali Rajakaruna,Chamila Rathnayake,Kit Yan Chan,Iain Murray "Image deblurring for navigation systems of vision impaired people using sensor fusion data" Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), 2014 IEEE Ninth International Conference on Year: 2014.

[6]Jing Wang, Ke Lu, Qian Wang, and Jie Jia "Kernel Optimization for Blind Motion Deblurring with Image Edge Prior" Hindawi Publishing Corporation Mathematical Problems in Engineering Volume 2012, Article ID 639824, 10 pages doi:10.1155/2012/639824.

[7]Long Mai,Feng Liu "Kernel fusion for better image deblurring" 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pages: 371 - 380, DOI: 10.1109/CVPR.2015.7298634.

[8]Jinshan Pan, Zhe Hu,Zhixun Su,Ming-Hsuan Yang "Deblurring Text Images via L0-Regularized Intensity and Gradient Prior" 2014 IEEE Conference on Computer Vision and Pattern Recognition Pages: 2901 - 2908, DOI: 10.1109/CVPR.2014.371.

[9]Nam-Yong Lee "Block-iterative Richardson-Lucy methods for image deblurring" Lee EURASIP Journal on Image and Video Processing (2015) Springer 2015:14 DOI 10.1186/s13640-015-0069-2.

[10]Linyang He, Gang Li,and Jinghong Liu "Joint Motion Deblurring and Superresolution from Single Blurry Image" Hindawi Publishing Corporation Mathematical Problems in Engineering Volume 2015, Article ID 965690.

[11]Tae Hyun Kim and Kyoung Mu Lee "Generalized Video Deblurring for Dynamic Scenes" 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Year: 2015 Pages: 5426 - 5434, DOI: 10.1109/CVPR.2015.7299181.

[12]Wei-Sheng Lai; Jian-Jiun Ding; Yen-Yu Lin; Yung-Yu Chuang "Blur kernel estimation using normalized color-line priors" 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Year: 2015 Pages: 64 - 72, DOI: 10.1109/CVPR.2015.7298601.

[13]Neeraj Kumar, Rahul Nallamothu, Amit Sethi "Neural Network Based Image Deblurring" Neural Network Applications in Electrical Engineering (NEUREL), 2012 11th Symposium on Year: 2012 IEEE Pages: 219 - 222, DOI: 10.1109/NEUREL.2012.6420015.

[14]J.Amudha, N.Pradeepa, R.Sudhakar "A Survey on Digital Image Restoration" ELSEVIER Procedia Engineering, Volume 38, 2012, Pages 2378-2382.

[15]Haichao Zhang,David Wipf,Yanning Zhang "Multi-image Blind Deblurring Using a Coupled Adaptive Sparse Prior" Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on Year: 2013 Pages: 1051 - 1058, DOI: 10.1109/CVPR.2013.140.

[16]Neeraj Kumar, Rahul Nallamothu, Amit Sethi "Neural Network Based Image Deblurring" Neural Network Applications in Electrical Engineering (NEUREL), 2012 IEEE 11th Symposium onYear: 2012 Pages: 219 - 222, DOI: 10.1109/NEUREL.2012.6420015.

[17]Amudha.J,Pradeepa.N,Sudhakar.R " A Survey on Digital Image Restoration" ELSEVIER Procedia Engineering 38 (2012) 2378 – 2382.

[18]Alex Krizhevsky , Ilya Sutskever , Geoffrey E. Hinton "Imagenet classification with deep convolutional neural networks" CiteSeer Document Advances in Neural Information Processing Systems 2012.

[19]Jian Sun; Wenfei Cao; Zongben Xu; Jean Ponce "Learning a convolutional neural network for non-uniform motion blur removal" 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Year: 2015 Pages: 769 - 777, DOI: 10.1109/CVPR.2015.729867.

[20]Michal Hradis, Jan Kotera, Pavel Zemˇcík, Filip Šroubek "Convolutional Neural Networks for Direct Text Deblurring" British Machine Vision Conference 2015 September.

[21]Li Xu, Jimmy SJ. Ren, Ce Liu, Jiaya Jia "Deep Convolutional Neural Network for Image Deconvolution" conference on Advances in Neural Information Processing Systems 27 (NIPS 2014).

[22]C. Gonzalez Richard E. Woods "Digital Image Processing" Book Third Edition Rafael Interactive Pearson International Edition prepared by Pearson Education PEARSON Prentice Hall.

[23]Ray Smith Google Inc. theraysmith@gmail.com "An Overview of the Tesseract OCR Engine" Google Inc OSCON 2007.

[24]Marion A.Hersh, Michael A.Johnson "Assistive technology for Visually Impaired and Blind people" Book by Springer ISBN 978-1-84628-866.

[25]Ratnakar Dash "Parameter Estimation for Image Restoration" PhD thsis NIT Rourkela, Orrisa,India March 2012.

[26]Zohair Al-Ameen,Ghazali Bin Sulong,Md. Gapar Md. Johar "Computer Forensics and Image Deblurring: An Inclusive Investigation" IJMECS Vol.5, No. 11, November 2013 PP.42-48, DOI: 10.5815/ijmecs.2013.11.06.