research-article

Super-resolution of single text image by sparse representation

Authors:

Franck Lebourgeois,

Adel M. AlimiAuthors Info & Claims

DAR '12: Proceeding of the workshop on Document Analysis and Recognition

Pages 22 - 29

https://doi.org/10.1145/2432553.2432558

Published: 16 December 2012 Publication History

Abstract

This paper addresses the problem of generating a super-resolved text image from a single low-resolution image. The proposed Super-Resolution (SR) method is based on sparse coding which suggests that image patches can be well represented as a sparse linear combination of elements from a suitably chosen learned dictionary. Toward this strategy, a High-Resolution/Low-Resolution (HR/LR) patch pair data base is collected from high quality character images. To our knowledge, it is the first generic database allowing SR of text images may be contained in documents, signs, labels, bills, etc. This database is used to train jointly two dictionaries. The sparse representation of a LR image patch from the first dictionary can be applied to generate a HR image patch from the second dictionary. The performance of such approach is evaluated and compared visually and quantitatively to other existing SR methods applied to text images. In addition, we examine the influence of text image resolution on automatic recognition performance and we further justify the effectiveness of the proposed SR method compared to others.

References

[1]

M. Aharon, M. Elad, and A. Bruckstein. The k-svd: An algorithm for designing of overcomplete dictionaries for sparse representation. IEEE Trans. On Signal Processing, 54(11): 4311--4322, November 2006.

Digital Library

[2]

C. Atkins, C. Bouman, and J. Allebach. Optimal image scaling using pixel classification. IEEE Int. Conf. on Image Processing, 3: 864--867, October 2001.

[3]

S. Baker and T. Kanade. Limits on super-resolution and how to break them. PAMI, 24(9): 1167--1183, September 2002.

Digital Library

[4]

S. Battiato, G. Gallo, and F. Stanco. Smart interpolation by anisotropic diffusion. Int. Conf. on Image Analysis and Processing, pages 572--577, September 2003.

Digital Library

[5]

M. Ben-Ezra, Z. C. Lin, and B. Wilburn. Penrose pixels: Superresolution in the detector layout domain. ICCV, pages 1--8, 2007.

[6]

D. Capel. Image mosaicing and super-resolution. University of Oxford, 2001.

Digital Library

[7]

H. Chang, D. Yeung, and Y. Xiong. Super-resolution through neighbor embedding. CVPR, 1: 275--282, 2004.

[8]

S. S. Chen, D. Donoho, and M. Saunders. Atomic decomposition by basis pursuit. SIAM Review, 43(1): 129--59, 2001.

Digital Library

[9]

G. Dalley, W. Freeman, and J. Marks. Single-frame text superresolution: a bayesian approach. In Proceedings of IEEE International Conference of Image Processing, pages 3295--3298, 2004.

[10]

D. Datsenko and M. Elad. Example-based single image super-resolution: A global map approach with outlier rejection. Journal of Multidimensional Systems and Signal Processing, 18(2--3): 103--121, 2007.

Digital Library

[11]

D. L. Donoho. For most large underdetermined systems of equations, the minimal {'-norm near-solution approximates the sparsest nearsolution. Communications on Pure and Applied Mathematics, 59: 907--934, July 2006.

[12]

W. Freeman, T. Jones, and E. Pasztor. Example-based superresolution. IEEE Computer Graphics and Applications, 22(2): 55--65, 2002.

Digital Library

[13]

W. T. Freeman, E. C. Pasztor, and O. T. Carmichael. Learning low-level vision. IJCV, 40(1): 25--47, 2000.

Digital Library

[14]

D. Glasner, S. Bagon, and M. Irani. Super-resolution from a single image. ICCV, pages 349--356, October 2009.

[15]

H. Greenspan, C. Anderson, and S. Akber. Image enhancement by nonlinear extrapolation in frequency space. IEEE Trans. on Image Processing, 9(6), 2000.

Digital Library

[16]

M. Irani and S. Peleg. Motion analysis for image enhancement: Resolution, occlusion and transparency. Journal of Visual Communication and Image Representation, 4(4): 324--335, 1993.

[17]

H. Lee, A. Battle, R. Raina, and A. Y. Ng. Efficient sparse coding algorithms. Advances in Neural Information Processing Systems, 2007.

[18]

X. Li and M. Orchard. New edge-directed interpolation. IEEE Trans. Image Process, 10: 1521--1527, 2001.

Digital Library

[19]

Z. Lin and H. Shum. Fundamental limits of reconstruction based superresolution algorithms under local translation. PAMI, 2004.

Digital Library

[20]

H. Luong and W. Philips. Non-local text image reconstruction. ICDAR, 1: 546--550, 2007.

Digital Library

[21]

H. Luong and W. Philips. Robust reconstruction of lowresolution document images by exploiting repetitive character behavior. IJDAR, 11(1): 39--51, 2008.

Digital Library

[22]

Q. H. Luong. Advanced image and video resolution enhancement techniques. 2009.

[23]

S. Mallat and Z. Zhang. Matching pursuit in a time-frequency dictionary. IEEE Transactions on Signal Processing, 41: 3397--3415, 1993.

Digital Library

[24]

G. Navarro. A guided tour to approximate string matching. ACM Computing Surveys, 33(1): 31--88, 2001.

Digital Library

[25]

B. Olshausen and D. Field. Sparse coding of sensory inputs. Cur. Op. Neurobiology, 14(4): 481--487, 2004.

[26]

B. A. Olshausen and D. J. Field. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381: 607--609, 1996.

[27]

B. A. Olshausen and D. J. Field. Sparse coding with an overcomplete basis set: A strategy employed by v1? Vision Research, 37: 3311--3325, 1997.

[28]

Y. Pati, R. Rezaiifar, and P. Krishnaprasad. Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition. Proc. of the 27th Annual Asilomar Conference on Signals, Systems, and Computers, 1993.

[29]

S. Rice. Measuring the accuracy of page-reading systems. University of Nevada, 1996.

Digital Library

[30]

C. Staelin, D. Greig, M. Fischer, and R. Maurer. Neural network image scaling using spatial errors. Tech. Rep. HPL-2003-26R1, HP Labs, Israel, 1978.

[31]

G. Sun and C. Qin. Single image super-resolution via sparse representation in gradient domain. International Conference on Multimedia Information Networking and Security, 2011.

Digital Library

[32]

J. Sun, Z. Xu, and H. Shum. Image super-resolution using gradient profile prior. CVPR, 2008.

[33]

J. Sun, N.-N. Zheng, H. Tao, and H. Shum. Image hallucination with primal sketch priors. CVPR, 2003.

[34]

M. F. Tappen, B. C. Ruseel, and W. T. Freeman. Exploiting the sparse derivative prior for super-resolution and image demosaicing. In Third International Workshop on Statistical and Computational Theories of Vision, ICCV, 2003.

[35]

www.freeocr.com.

[36]

www.newocr.com.

[37]

www.sciweavers.org/free-online ocr.

[38]

J. Yang, J. Wright, T. Huang, and Y. Ma. Image super-resolution as sparse representation of raw image patches. CVPR, 2008.

[39]

J. Yang, J. Wright, T. Huang, and Y. Ma. Image super-resolution via sparse representation. IEEE Transactions on Image Processing, 19(11): 2861--2873, 2010.

Digital Library

Cited By

Walha RAouini A(2024)Scene text image super-resolution using multi-scale convolutional neural network with skip connectionsApplied Intelligence10.1007/s10489-024-05471-554:8(5931-5943)Online publication date: 1-Apr-2024
https://dl.acm.org/doi/10.1007/s10489-024-05471-5
Lee HJung CKim C(2020)Blind Deblurring of Text Images Using a Text-Specific Hybrid DictionaryIEEE Transactions on Image Processing10.1109/TIP.2019.293373929(710-723)Online publication date: 2020
https://doi.org/10.1109/TIP.2019.2933739
Quan YYang JChen YXu YJi H(2020)Collaborative Deep Learning for Super-Resolving Blurry Text ImagesIEEE Transactions on Computational Imaging10.1109/TCI.2020.29817586(778-790)Online publication date: 2020
https://doi.org/10.1109/TCI.2020.2981758
Show More Cited By

Index Terms

Super-resolution of single text image by sparse representation
1. Applied computing
  1. Document management and text processing
    1. Document capture
      1. Optical character recognition
2. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision representations
        Image representations
      2. Computer vision tasks

Recommendations

Hyperspectral image super-resolution through clustering-based sparse representation
Abstract
Promoting the spatial resolution of hyperspectral sensors is expected to improve computer vision tasks. However, due to the physical limitations of imaging sensors, the hyperspectral image is often of low spatial resolution. In this paper, we ...
Super-resolution of hyperspectral image via superpixel-based sparse representation

In this paper, a novel superpixel-based sparse representation (SSR) model is proposed for hyperspectral image (HSI) super-resolution. Specifically, given a HSI with low spatial resolution and a multispectral image (MSI) with high spatial resolution, the ...
Context-aware single image super-resolution using sparse representation and cross-scale similarity

Methods for single image super-resolution (SR) are broadly divided into two categories: (i) edge-focused SR and (ii) example-based SR. Edge-focused methods are focused on producing sharp edges with minimal artifacts; however, these methods cannot ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

DAR '12: Proceeding of the workshop on Document Analysis and Recognition

December 2012

162 pages

ISBN:9781450317979

DOI:10.1145/2432553

Program Chairs:
A. G. Ramakrishnan
IISc, Bangalore
,
Sitaram Ramachandrula
HP Labs, Bangalore

Copyright © 2012 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 16 December 2012

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

DAR '12

DAR '12: Workshop on Document Analysis and Recognition

December 16, 2012

Mumbai, India

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

15
Total Citations
View Citations
280
Total Downloads

Downloads (Last 12 months)6
Downloads (Last 6 weeks)0

Reflects downloads up to 11 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Walha RAouini A(2024)Scene text image super-resolution using multi-scale convolutional neural network with skip connectionsApplied Intelligence10.1007/s10489-024-05471-554:8(5931-5943)Online publication date: 1-Apr-2024
https://dl.acm.org/doi/10.1007/s10489-024-05471-5
Lee HJung CKim C(2020)Blind Deblurring of Text Images Using a Text-Specific Hybrid DictionaryIEEE Transactions on Image Processing10.1109/TIP.2019.293373929(710-723)Online publication date: 2020
https://doi.org/10.1109/TIP.2019.2933739
Quan YYang JChen YXu YJi H(2020)Collaborative Deep Learning for Super-Resolving Blurry Text ImagesIEEE Transactions on Computational Imaging10.1109/TCI.2020.29817586(778-790)Online publication date: 2020
https://doi.org/10.1109/TCI.2020.2981758
Lin KLiu YLi TLiu SLi G(2019)Text Image Super-Resolution by Image Matting and Text Label Supervision2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)10.1109/CVPRW.2019.00222(1722-1727)Online publication date: Jun-2019
https://doi.org/10.1109/CVPRW.2019.00222
Wongso RLuwinda FWilliem (2018)Evaluation of Deep Super Resolution Methods for Textual ImagesProcedia Computer Science10.1016/j.procs.2018.08.181135(331-337)Online publication date: 2018
https://doi.org/10.1016/j.procs.2018.08.181
Walha RDrira FLebourgeois FGarcia CAlimi A(2018)Handling noise in textual image resolution enhancement using online and offline learned dictionariesInternational Journal on Document Analysis and Recognition10.1007/s10032-017-0294-621:1-2(137-157)Online publication date: 1-Jun-2018
https://dl.acm.org/doi/10.1007/s10032-017-0294-6
Walha RDrira FLebourgeois FAlimi AGarcia C(2016)Resolution enhancement of textual images: a survey of single image‐based methodsIET Image Processing10.1049/iet-ipr.2015.033410:4(325-337)Online publication date: Apr-2016
https://doi.org/10.1049/iet-ipr.2015.0334
Walha RDrira FLebourgeois FGarcia CAlimi A(2015)Joint denoising and magnification of noisy Low-Resolution textual imagesProceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR)10.1109/ICDAR.2015.7333886(871-875)Online publication date: 23-Aug-2015
https://dl.acm.org/doi/10.1109/ICDAR.2015.7333886
Walha RDrira FLebourgeois FGarcia CAlimi A(2015)Resolution enhancement of textual images via multiple coupled dictionaries and adaptive sparse representation selectionInternational Journal on Document Analysis and Recognition10.1007/s10032-014-0235-618:1(87-107)Online publication date: 1-Mar-2015
https://dl.acm.org/doi/10.1007/s10032-014-0235-6
Walha RDrira FLebourgeois FGarcia CAlimi A(2014)Sparse Coding with a Coupled Dictionary Learning Approach for Textual Image Super-resolutionProceedings of the 2014 22nd International Conference on Pattern Recognition10.1109/ICPR.2014.763(4459-4464)Online publication date: 24-Aug-2014
https://dl.acm.org/doi/10.1109/ICPR.2014.763
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten