research-article

An efficient parametrization of character degradation model for semi-synthetic image generation

Authors:

Jean Philippe DomengerAuthors Info & Claims

HIP '13: Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing

Pages 29 - 35

https://doi.org/10.1145/2501115.2501127

Published: 24 August 2013 Publication History

Get Access

Abstract

This paper presents an efficient parametrization method for generating synthetic noise on document images. By specifying the desired categories and amount of noise, the method is able to generate synthetic document images with most of degradations observed in real document images (ink splotches, white specks or streaks). Thanks to the ability of simulating different amount and kind of noise, it is possible to evaluate the robustness of many document image analysis methods. It also permits to generate data for algorithms that employ a learning process. The degradation model presented in [7] needs eight parameters for generating randomly noise regions. We propose here an extension of this model which aims to set automatically the eight parameters to generate precisely what a user wants (amount and category of noise). Our proposition consists of three steps. First, N_sp seed-points (i.e. centres of noise regions) are selected by an adaptive procedure. Then, these seed-points are classified into three categories of noise by using a heuristic rule. Finally, each size of noise region is set using a random process in order to generate degradations as realistic as possible.

References

[1]

H. S. Baird. The State of the Art of Document Image Degradation Modeling. In In Proc. of 4 th IAPR International Workshop on Document Analysis Systems, Rio de Janeiro, pages 1--16, Rio de Janeiro, Brazil, 2000.

Google Scholar

[2]

M. Delalandre, E. Valveny, T. Pridmore, and D. Karatzas. Generation of Synthetic Documents for Performance Evaluation of Symbol Recognition & Spotting Systems. Int. J. Doc. Anal. Recognit., 13(3):187--207, Sept. 2010.

Digital Library

Google Scholar

[3]

D. D. Jian Zhai, Liu Wenyin and Q. Li. A Line Drawings Degradation Model for Performance Characterization. In Proc. 7th ICDAR, pages 1020--1024, Edinburgh, Scotland, August 2003.

Digital Library

Google Scholar

[4]

T. Kanungo, R. Haralick, H. Baird, W. Stuezle, and D. Madigan. A statistical, Nonparametric Methodology for Document Degradation Model Validation. IEEE Trans. Pattern Anal. Mach. Intell., 22(11):1209--1223, 2000.

Digital Library

Google Scholar

[5]

T. Kanungo, R. M. Haralick, and I. Phillips. Global and Local Document Degradation Models. In Proc. of the ICDAR, pages 730--734, Tsukuba Science City, Japan, Oct. 1993.

Crossref

Google Scholar

[6]

V. Kieu, N. Journet, M. Visani, R. Mullot, and J. P. Domenger. Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes. In Accepted for publication in Document Analysis and Recognition (ICDAR), 2013 International Conference on, 2013.

Google Scholar

[7]

V. Kieu, M. Visani, N. Journet, J. P. Domenger, and R. Mullot. A Character Degradation Model for Grayscale Ancient Document Images. In Proc. of the ICPR, pages 685--688, Tsukuba Science City, Japan, Nov. 2012.

Google Scholar

[8]

Y. Li, D. Lopresti, G. Nagy, and A. Tomkins. Validation of Image Defect Models for Optical Character Recognition. IEEE Trans. Pattern Anal. Mach. Intell., 18(2):99--108, Feb. 1996.

Digital Library

Google Scholar

[9]

R. Loce and W. Lama. Halftone Banding due to Vibrations in A Xerographic Image Bar Printer. Journal of Imaging Technology, 16(1):6--11, 1990.

Google Scholar

[10]

R. F. Moghaddam and M. Cheriet. Low Quality Document Image Modeling and Enhancement. In Int. J. Doc. Anal. Recognit, volume 11, pages 183--201, Berlin, Heidelberg, March 2009. Springer.

Digital Library

Google Scholar

[11]

M. Mori, A. Suzuki, A. Shio, and S. Ohtsuka. Generating New Samples from Handwritten Numerals Based on Point Correspondence. In Proc. 7th Int. Workshop on Frontiers in Handwriting Recognition, pages 281--290, Amsterdam, Netherlands, 2000.

Google Scholar

[12]

E. B. Smith. Modeling Image Degradations for Improving OCR. In 16th European Signal Processing Conference (EUSIPCO), pages 1--5, Lausanne, Switzerland, August 2008.

Google Scholar

[13]

T. Varga and H. Bunke. Effects of Training Set Expansion in Handwriting Recognition Using Synthetic Data. In Proc. 11th Conf. of the Int. Graphonomics Society, pages 200--203, Scottsdale, AZ, USA, Nov. 2003. Citeseer.

Google Scholar

[14]

T. Varga and H. Bunke. Generation of Synthetic Training Data for an HMM-based Handwriting Recognition System. In Proc. 7th ICDAR, pages 618--622, Edinburgh, Scotland, August 2003.

Digital Library

Google Scholar

Cited By

View all

Premachandra HYamada MPremachandra CKawanaka H(2022)Low-Computational-Cost Algorithm for Inclination Correction of Independent Handwritten Digits on MicrocontrollersElectronics10.3390/electronics1107107311:7(1073)Online publication date: 29-Mar-2022
https://doi.org/10.3390/electronics11071073
Garai ABiswas SMandal SChaudhuri B(2020)A Method to Generate Synthetically Warped Document ImageComputer Vision and Image Processing10.1007/978-981-15-4015-8_24(270-280)Online publication date: 29-Mar-2020
https://doi.org/10.1007/978-981-15-4015-8_24
Castro-Bleda MEspaña-Boquera SPastor-Pellicer JZamora-Martínez F(2019)The NoisyOffice Database: A Corpus To Train Supervised Machine Learning Filters For Image ProcessingThe Computer Journal10.1093/comjnl/bxz098Online publication date: 2-Dec-2019
https://doi.org/10.1093/comjnl/bxz098
Show More Cited By

Recommendations

Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes
ICDAR '13: Proceedings of the 2013 12th International Conference on Document Analysis and Recognition

This article presents a method for generating semi-synthetic images of old documents where the pages might be torn (not flat). By using only 2D deformation models, most existing methods give non-realistic synthetic document images. Thus, we propose to ...
Investigating the Effect of Using Synthetic and Semi-synthetic Images for Historical Document Font Classification
Document Analysis Systems
Abstract
This paper studies the effect of using various data augmentation by synthetization approaches on historical image data, particularly for font classification. Historical document image datasets often lack the appropriate size to train and evaluate ...
Low resolution character recognition by dual eigenspace and synthetic degraded patterns
HDP '04: Proceedings of the 1st ACM workshop on Hardcopy document processing

As the rapid progress of digital imaging technology, the requirements of character recognition for text embedded in image increase dramatically. Many image text characters are in low resolution with heavy degradation. Traditional OCR methods don't have ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

HIP '13: Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing

August 2013

141 pages

ISBN:9781450321150

DOI:10.1145/2501115

Editors:
Volker Märgner
Technische Universität Braunschweig, Germany
,
Volkmar Frinken
Computer Vision Center, Barcelona, Spain
,
Bill Barrett
Brigham Young University
,
R. Manmatha
UMass Amherst
,
Program Chairs:
Volkmar Frinken
Computer Vision Center, Barcelona, Spain
,
Bill Barrett
Brigham Young University
,
R. Manmatha
UMass Amherst
,
Volker Märgner
Technische Universität Braunschweig, Germany

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 the author(s) 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: 24 August 2013

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Agence Nationale de la Recherche

Conference

HIP '13

Sponsor:

FamilySearch

HIP '13: 2nd International Workshop on Historical Document Imaging and Processing

August 24, 2013

District of Columbia, Washington, USA

Acceptance Rates

HIP '13 Paper Acceptance Rate 18 of 31 submissions, 58%;

Overall Acceptance Rate 52 of 90 submissions, 58%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
65
Total Downloads

Downloads (Last 12 months)1
Downloads (Last 6 weeks)0

Reflects downloads up to 24 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Premachandra HYamada MPremachandra CKawanaka H(2022)Low-Computational-Cost Algorithm for Inclination Correction of Independent Handwritten Digits on MicrocontrollersElectronics10.3390/electronics1107107311:7(1073)Online publication date: 29-Mar-2022
https://doi.org/10.3390/electronics11071073
Garai ABiswas SMandal SChaudhuri B(2020)A Method to Generate Synthetically Warped Document ImageComputer Vision and Image Processing10.1007/978-981-15-4015-8_24(270-280)Online publication date: 29-Mar-2020
https://doi.org/10.1007/978-981-15-4015-8_24
Castro-Bleda MEspaña-Boquera SPastor-Pellicer JZamora-Martínez F(2019)The NoisyOffice Database: A Corpus To Train Supervised Machine Learning Filters For Image ProcessingThe Computer Journal10.1093/comjnl/bxz098Online publication date: 2-Dec-2019
https://doi.org/10.1093/comjnl/bxz098
Garg RChaudhury S(2016)Automatic Selection of Parameters for Document Image Enhancement Using Image Quality Assessment2016 12th IAPR Workshop on Document Analysis Systems (DAS)10.1109/DAS.2016.53(422-427)Online publication date: Apr-2016
https://doi.org/10.1109/DAS.2016.53
Luyen DCarel EOgier JBurie J(2015)A character degradation model for color document imagesProceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR)10.1109/ICDAR.2015.7333873(806-810)Online publication date: 23-Aug-2015
https://dl.acm.org/doi/10.1109/ICDAR.2015.7333873
Mehri MKieu VMhiri MHéroux PGomez-Krämer PMahjoub MMullot R(2013)Robustness Assessment of Texture Features for the Segmentation of Ancient DocumentsProceedings of the 2013 27th Brazilian Symposium on Software Engineering10.1109/DAS.2014.22(293-297)Online publication date: 1-Oct-2013
https://dl.acm.org/doi/10.1109/DAS.2014.22

View Options

Get Access

Login options

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

Cited By

Recommendations

Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes

Investigating the Effect of Using Synthetic and Semi-synthetic Images for Historical Document Font Classification

Low resolution character recognition by dual eigenspace and synthetic degraded patterns