Article

ICDAR 2021 Competition on Time-Quality Document Image Binarization

Authors:

Rafael Dueire Lins,

Rodrigo Barros Bernardino,

Elisa Barney Smith,

Ergina KavallieratouAuthors Info & Claims

Document Analysis and Recognition – ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5–10, 2021, Proceedings, Part IV

Pages 708 - 722

https://doi.org/10.1007/978-3-030-86337-1_47

Published: 05 September 2021 Publication History

Abstract

The ICDAR 2021 Time-Quality Binarization Competition assessed the performance of 12 new and 49 other previously published binarization algorithms for scanned document images. Four test sets of “real-world” documents with different features were used. For each test set, the top twenty algorithms in the quality of the resulting two-tone images had their average processing time presented, yielding an account of their time complexity.

References

[1]

Akbari, Y., Britto Jr., A.S., Al-Maadeed, S., Oliveira, L.S.: Binarization of degraded document images using convolutional neural networks based on predicted two-channel images. In: ICDAR (2019)

[2]

Azad, R., Asadi-Aghbolaghi, M., Fathy, M., Escalera, S.: Bi-directional ConvLSTM U-net with densley connected convolutions. In: ICCVW 2019, pp. 406–415 (2019)

[3]

Barney Smith, E.H., Likforman-Sulem, L., Darbon, J.: Effect of pre-processing on binarization. In: Document Recognition and Retrieval XVII, p. 75340H (2010)

[4]

Bataineh B, Abdullah SNHS, and Omar K An adaptive local binarization method for document images based on a novel thresholding method and dynamic windows Pattern Recogn. Lett. 2011 32 14 1805-1813

Digital Library

[5]

Bera SK, Ghosh S, Bhowmik S, Sarkar R, and Nasipuri M A non-parametric binarization method based on ensemble of clustering algorithms Multimed. Tools Appl. 2020 80 5 7653-7673

Digital Library

[6]

Bernardino, R., Lins, R., Jesus, D.M.: A quality and time assessment of binarization algorithms. In: 2019 15th IAPR ICDAR, pp. 1444–1450 (2019)

[7]

Bernsen, J.: Dynamic thresholding of gray-level images. In: International Conference on Pattern Recognition, pp. 1251–1255 (1986)

[8]

Su B, Lu S, and Tan CL Robust document image binarization technique for degraded document images Trans. Image Process. 2013 22 4 1408-1417

Digital Library

[9]

Bradley D and Roth G Adaptive thresholding using the integral image J. Graph. Tools 2007 12 2 13-21

[10]

Calvo-Zaragoza J and Gallego AJ A selectional auto-encoder approach for document image binarization Pattern Recogn. 2019 86 37-47

[11]

Clausner, C., Papadopoulos, C., Pletschacher, S., Antonacopoulos, A.: The ENP image and ground truth dataset of h. newspapers. In: ICDAR’15, pp. 931–935 (2015)

[12]

Congalton RG A review of assessing the accuracy of classifications of remotely sensed data Remote Sens. Environ. 1991 37 1 35-46

[13]

Doyle W Operations useful for similarity-invariant pattern recognition J. ACM 1962 9 2 259-267

Digital Library

[14]

Gatos, B., Ntirogiannis, K., Pratikakis, I.: ICDAR 2009 document image binarization contest (DIBCO 2009). In: 2009 10th ICDAR, pp. 1375–1382. IEEE (2009)

[15]

Gattal, A., Abbas, F., Laouar, M.R.: Automatic parameter tuning of K-means algorithm for document binarization. In: 7th ICSENT, pp. 1–4. ACM Press (2018)

[16]

Glasbey C An analysis of histogram-based thresholding algorithms Graph. Model. Image Process. 1993 55 6 532-537

Digital Library

[17]

Hadjadj Z, Meziane A, Cherfa Y, Cheriet M, and Setitra I Campilho A and Karray F ISauvola: improved Sauvola’s algorithm for document image binarization Image Analysis and Recognition 2016 Cham Springer 737-745

[18]

Howe NR Document binarization with automatic parameter tuning IJDAR 2013 16 3 247-258

Digital Library

[19]

Huang LK and Wang MJJ Image thresholding by minimizing the measures of fuzziness Pattern Recogn. 1995 28 1 41-51

[20]

Jia F, Shi C, He K, Wang C, and Xiao B Degraded document image binarization using structural symmetry of strokes Pattern Recogn. 2018 74 225-240

Digital Library

[21]

Johannsen, G., Bille, J.: A threshold selection method using information measures. In: International Conference Pattern Recognition, pp. 140–143 (1982)

[22]

Kapur, J., Sahoo, P., Wong, A.: A new method for gray-level picture thresholding using the entropy of the histogram. Comput. Vis. Graph. Image Process. 29(1), 140

[23]

Kavallieratou, E.: A binarization algorithm specialized on document images and photos. In: ICDAR 2005, no. 1, pp. 463–467 (2005)

[24]

Kavallieratou, E., Stathis, S.: Adaptive binarization of historical document images. In: Proceedings - International Conference on Pattern Recognition, vol. 3, pp. 742–745 (2006)

[25]

Khurshid, K., Siddiqi, I., Faure, C., Vincent, N.: Comparison of Niblack inspired binarization methods for ancient documents. In: SPIE, p. 72470U (2009)

[26]

Kittler J and Illingworth J Minimum error thresholding Pattern Recogn. 1986 19 1 41-47

Digital Library

[27]

Kong X, Sun G, Wu Q, Liu J, and Lin F Shi Z, Mercier-Laurent E, and Li J Hybrid pyramid U-Net model for brain tumor segmentation Intelligent Information Processing IX 2018 Cham Springer 346-355

[28]

Li C and Tam P An iterative algorithm for minimum cross entropy thresholding Pattern Recogn. Lett. 1998 19 8 771-776

Digital Library

[29]

Lins RD Kamel M and Campilho A A taxonomy for noise in images of paper documents - the physical noises Image Analysis and Recognition 2009 Heidelberg Springer 844-854

Digital Library

[30]

Lins, R.D., Almeida, M.M.D., Bernardino, R.B., Jesus, D., Oliveira, J.M.: Assessing binarization techniques for document images. In: DocEng’17, pp. 183–192 (2017)

[31]

Lins RD, Guimarães Neto M, França Neto L, and Galdino Rosa L An environment for processing images of historical documents Microprocess. Microprogram. 1994 40 10–12 939-942

Digital Library

[32]

Lins, R.D., Kavallieratou, E., Barney Smith, E., Bernardino, R.B., de Jesus, D.M.: ICDAR 2019 Time-Quality Binarization Competition. In: ICDAR, pp. 1539–1546 (2019)

[33]

Lins, R.D., Simske, S.J., Bernardino, R.B.: DocEng’2020 time-quality competition on binarizing photographed documents. In: DocEng’20, pp. 1–4. ACM (2020)

[34]

Lins RD, Torreão G, and Pereira e Silva G Ogier J-M, Liu W, and Lladós J Content recognition and indexing in the LiveMemory platform Graphics Recognition. Achievements, Challenges, and Evolution 2010 Heidelberg Springer 220-230

[35]

Lu D, Huang X, and Sui LX Binarization of degraded document images based on contrast enhancement IJDAR 2018 21 1–2 123-135

Digital Library

[36]

Lu S, Su B, and Tan CL Document image binarization using background estimation and stroke edges IJDAR 2010 13 4 303-314

Digital Library

[37]

Lu, W., Songde, M., Lu, H.: An effective entropic thresholding for ultrasonic images. In: 14th ICPR, vol. 2, pp. 1552–1554 (1998)

[38]

Mello, C.A.B., Lins, R.D.: Image segmentation of historical documents. In: Visual 2000 (2000)

[39]

Mustafa, W.A., Abdul Kader, M.M.M.: Binarization of document image using optimum threshold modification. J. Phys.: C. Ser. 1019(1), 012022 (2018)

[40]

Niblack W An Introduction to Digital Image Processing 1985 Copenhagen Strandberg Publishing Company

Digital Library

[41]

Ntirogiannis K, Gatos B, and Pratikakis I Performance evaluation methodology for historical document image binarization IEEE Trans. Image Process. 2013 22 2 595-609

Digital Library

[42]

Oliveira, S.A., Seguin, B., Kaplan, F.: dhSegment: a generic deep-learning approach for document segmentation. CoRR abs/1804.1 (2018)

[43]

Otsu N A threshold selection method from gray-level histograms IEEE Trans. Syst. Man Cybern. 1979 9 1 62-66

[44]

Paredes, R., Kavallieratou, E., Lins, R.D.: ICFHR 2010 contest: quantitative evaluation of binarization algorithms. In: 12th ICFHR, pp. 733–736. IEEE (2010)

[45]

Powers DMW Evaluation: from precision, recall and F-measure to ROC, informedness, markedness & correlation J. M. L. Technol. 2011 2 1 37-63

[46]

Pratikakis, I., et al.: ICDAR 2019 competition on document image binarization. In: ICDAR, No. November 2019 (2019)

[47]

Prewitt JMS and Mendelsohn ML The analysis of cell images Ann. N. Y. Acad. Sci. 2006 128 3 1035-1053

[48]

Pun T Entropic thresholding, a new approach Comput. Graph. Image Process. 1981 16 3 210-239

[49]

Saddami, K., Afrah, P., Mutiawani, V., Arnia, F.: A new adaptive thresholding technique for binarizing ancient document. In: INAPR, pp. 57–61. IEEE (2018)

[50]

Saddami, K., Munadi, K., Away, Y., Arnia, F.: Combination local and global thresholding method for binarizing ancient Jawi document. JTIIK (2019)

[51]

Saddami, K., Munadi, K., Away, Y., Arnia, F.: Effective and fast binarization method for combined degradation on ancient documents. Heliyon (2019)

[52]

Saddami, K., Munadi, K., Muchallil, S., Arnia, F.: Improved thresholding method for enhancing Jawi binarization performance. In: ICDAR, vol. 1, pp. 1108–1113. IEEE (2017)

[53]

Sahoo P, Wilkins C, and Yeager J Threshold selection using Renyi’s entropy Pattern Recogn. 1997 30 1 71-84

[54]

Sauvola J, Pietikäinen M, and Pietikainem M Adaptive document image binarization Pattern Recogn. 2000 33 2 225-236

[55]

Sauvola, J., Seppanen, T., Haapakoski, S., Pietikainen, M.: Adaptive document binarization. In: ICDAR, vol. 1, pp. 147–152. IEEE Comput. Soc (1997)

[56]

Shanbhag AG Utilization of information measure as a means of image thresholding CVGIP: Graph. Models Image Process. 1994 56 5 414-419

Digital Library

[57]

Silva JMM, Lins RD, and Rocha VC Binarizing and filtering historical documents with back-to-front interference ACM SAC 2006 2006 853-858

[58]

da Silva, J.M.M., Lins, R.D.: Color document synthesis as a compression strategy. In: ICDAR (ICDAR), pp. 466–470 (2007)

[59]

Singh TR, Roy S, Singh OI, Sinam T, and Singh KM A new local adaptive thresholding technique in binarization IJCSI Int. J. Comput. Sci. Issues 2011 08 6 271-277

[60]

Souibgui, M.A., Kessentini, Y.: DE-GAN: a conditional generative adversarial network for document enhancement. Trans. Pattern Anal. Mach. Intell. 1 (2021)

[61]

Su, B., Lu, S., Tan, C.L.: Binarization of historical document images using the local maximum and minimum. In: 8th IAPR DAS, pp. 159–166. ACM Press (2010)

[62]

Tsai WH Moment-preserving thresolding: a new approach Comput. Vis. Graph. Image Process. 1985 29 3 377-393

[63]

Velasco, F.R.: Thresholding using the Isodata clustering algorithm. Technical report, OSD or Non-Service DoD Agency (1979)

[64]

Wolf, C., Doermann, D.: Binarization of low quality text using a Markov random field model. In: Object Recognition Supported by User Interaction for Service Robots, vol. 3, pp. 160–163. IEEE Computer Society (2002)

[65]

Wolf, C., Jolion, J.M., Chassaing, F.: Text localization, enhancement and binarization in multimedia documents. In: Object Recognition Supported by User Interaction for Service Robots, vol. 2, pp. 1037–1040. IEEE Computer Society (2003)

[66]

Yen JC, Chang FJCS, Yen JC, Chang FJ, and Chang S A new criterion for automatic multilevel thresholding Trans. Image Process. 1995 4 3 370-378

Digital Library

[67]

Zack GW, Rogers WE, and Latt SA Automatic measurement of sister chromatid exchange frequency J. Histochem. Cytochem. 1977 25 7 741-753

[68]

Zhou, L., Zhang, C., Wu, M.: D-linknet: Linknet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction. In: Computer Vision and Pattern Recognition (2018)

Cited By

Lins RChaves Gde F. P e Silva GVieira Tda Silva Barboza RSimske S(2024)Competition on Binarizing Photographed Document Images 2024 Quality, Time and Space ReportProceedings of the ACM Symposium on Document Engineering 202410.1145/3685650.3686793(1-12)Online publication date: 20-Aug-2024
https://dl.acm.org/doi/10.1145/3685650.3686793
Lins RNunes de Mello Dde Oliveira R(2024)Which is the most suitable scanner resolution for documents? Detailing the answer given to the question raised by Professor George NagyProceedings of the ACM Symposium on Document Engineering 202410.1145/3685650.3685672(1-4)Online publication date: 20-Aug-2024
https://dl.acm.org/doi/10.1145/3685650.3685672
Lins Rde F. Pe Silva GChaves Gda Silva Barboza RBernardino RSimske S(2023)Quality, Space and Time Competition on Binarizing Photographed Document ImagesProceedings of the ACM Symposium on Document Engineering 202310.1145/3573128.3604903(1-10)Online publication date: 22-Aug-2023
https://dl.acm.org/doi/10.1145/3573128.3604903
Show More Cited By

Recommendations

Direct binarization a quality-and-time efficient binarization strategy
DocEng '21: Proceedings of the 21st ACM Symposium on Document Engineering

Most of the best known binarization algorithms have grayscale conversion as a pre-processing step, before applying the binarization strategy itself. Many algorithms produce equally good or even better quality images if fed with only one component of the ...
Deep semantic binarization for document images
Abstract
Binarization is an essential pre-processing step for many document image analysis tasks. Binarization of handwritten documents is more challenging than printed documents because of the non-uniform density of ink and the variable thickness of ...
ICDAR 2011 Document Image Binarization Contest (DIBCO 2011)
ICDAR '11: Proceedings of the 2011 International Conference on Document Analysis and Recognition

DIBCO 2011 is the International Document Image Binarization Contest organized in the context of ICDAR 2011 conference. The general objective of the contest is to identify current advances in document image binarization for both machine-printed and ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

Document Analysis and Recognition – ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5–10, 2021, Proceedings, Part IV

Sep 2021

806 pages

ISBN:978-3-030-86336-4

DOI:10.1007/978-3-030-86337-1

Editors:
Josep Lladós
Universitat Autònoma de Barcelona, Barcelona, Spain
,
Daniel Lopresti
Lehigh University, Bethlehem, PA, USA
,
Seiichi Uchida
Kyushu University, Fukuoka-shi, Japan

© Springer Nature Switzerland AG 2021.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 05 September 2021

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

7
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 29 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Lins RChaves Gde F. P e Silva GVieira Tda Silva Barboza RSimske S(2024)Competition on Binarizing Photographed Document Images 2024 Quality, Time and Space ReportProceedings of the ACM Symposium on Document Engineering 202410.1145/3685650.3686793(1-12)Online publication date: 20-Aug-2024
https://dl.acm.org/doi/10.1145/3685650.3686793
Lins RNunes de Mello Dde Oliveira R(2024)Which is the most suitable scanner resolution for documents? Detailing the answer given to the question raised by Professor George NagyProceedings of the ACM Symposium on Document Engineering 202410.1145/3685650.3685672(1-4)Online publication date: 20-Aug-2024
https://dl.acm.org/doi/10.1145/3685650.3685672
Lins Rde F. Pe Silva GChaves Gda Silva Barboza RBernardino RSimske S(2023)Quality, Space and Time Competition on Binarizing Photographed Document ImagesProceedings of the ACM Symposium on Document Engineering 202310.1145/3573128.3604903(1-10)Online publication date: 22-Aug-2023
https://dl.acm.org/doi/10.1145/3573128.3604903
Sfikas GRetsinas GGatos B(2023)Document Binarization with Quaternionic Double Discriminator Generative Adversarial NetworkDocument Analysis and Recognition – ICDAR 2023 Workshops10.1007/978-3-031-41501-2_19(272-284)Online publication date: 21-Aug-2023
https://dl.acm.org/doi/10.1007/978-3-031-41501-2_19
Lins RBernardino RBarboza RSimske SWigington CHardy MBagley SSimske S(2022)Binarization of photographed documents image quality, processing time and size assessmentProceedings of the 22nd ACM Symposium on Document Engineering10.1145/3558100.3564159(1-10)Online publication date: 20-Sep-2022
https://dl.acm.org/doi/10.1145/3558100.3564159
Sukesh RSeuret MNicolaou AMayr MChristlein V(2022)A Fair Evaluation of Various Deep Learning-Based Document Image Binarization ApproachesDocument Analysis Systems10.1007/978-3-031-06555-2_52(771-785)Online publication date: 22-May-2022
https://dl.acm.org/doi/10.1007/978-3-031-06555-2_52
Lins RBernardino RBarboza ROliveira R(2022)The Winner Takes It All: Choosing the “best” Binarization Algorithm for Photographed DocumentsDocument Analysis Systems10.1007/978-3-031-06555-2_4(48-64)Online publication date: 22-May-2022
https://dl.acm.org/doi/10.1007/978-3-031-06555-2_4

View Options

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.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents