More Web Proxy on the site http://driver.im/

article

Segmentation of connected handwritten digits using Self-Organizing Maps

Authors:

Everton B. Lacerda,

Carlos A. B. MelloAuthors Info & Claims

Expert Systems with Applications: An International Journal, Volume 40, Issue 15

Pages 5867 - 5877

https://doi.org/10.1016/j.eswa.2013.05.006

Published: 01 November 2013 Publication History

Abstract

Segmentation is an important issue in document image processing systems as it can break a sequence of characters into its components. Its application over digits is common in bank checks, mail and historical document processing, among others. This paper presents an algorithm for segmentation of connected handwritten digits based on the selection of feature points, through a skeletonization process, and the clustering of the touching region via Self-Organizing Maps. The segmentation points are then found, leading to the final segmentation. The method can deal with several types of connection between the digits, having also the ability to map multiple touching. The proposed algorithm achieved encouraging results, both relating to other state-of-the-art algorithms and to possible improvements.

References

[1]

Multiagents to separating handwritten connected digits. IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans. v35. 1198-1202.

[2]

An overview of character recognition focused on off-line handwriting. IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews. v31. 216-233.

[3]

Blum, H. (1967). A transformation for extracting new descriptors of shape. In Models for the perception of speech and visual form (pp. 362-380). Cambridge.

[4]

Document page segmentation using neuro-fuzzy approach. Applied Soft Computing. v8. 118-126.

[5]

A survey of methods and strategies in character segmentation. IEEE Transactions on Pattern Analysis and Recognition. v18. 690-706.

[6]

A knowledge based system for extracting text-lines from mixed and overlapping text/graphics compound document images. Expert Systems with Applications. v39. 494-507.

[7]

Segmentation of simple- or multiple-touching handwritten numeral string using background and foreground analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. v22. 1304-1317.

[8]

Congedo, G., Dimauro, G., Impedovo, S., & Pirlo, G. (1995). Segmentation of numeric strings. In Third international conference on document analysis and recognition (Vol. 2, pp. 1038-1041). Montreal.

[9]

Support-vector networks. Machine Learning. v20. 273-297.

[10]

Dinneen, G. P. (1955). Programming pattern recognition. In Western joint computer conference (pp. 94-100). New York.

[11]

Pattern classification. 2nd ed. John Wiley and Sons, New York.

[12]

Self-organizing maps: Ordering, convergence properties and energy functions. Biological Cybernetics. v67. 47-55.

[13]

Fenrich, R., & Krishnamoorthy, S. (1990). Segmenting diverse quality handwritten digit strings in near real-time. In Proceedings of the fifth USPS advanced technology conference (pp. 523-537). Washington, D.C.

[14]

Forty years of research in character and document recognition. Pattern Recognition. v41. 2435-2446.

Digital Library

[15]

Digital image processing. 3rd ed. Prentice-Hall, Upper Saddle River.

[16]

Parallel thinning with two subiteration algorithms. Communications of the ACM. v32. 359-373.

[17]

MATLAB 6 complete course. Prentice-Hall, Sao Paulo.

[18]

. Computer and robot vision, 1992.Addison-Wesley.

[19]

The Elements of statistical learning. Springer series in statistics, 2009.2nd ed. Springer, New York.

[20]

Neural networks: A comprehensive foundation. 1999. 2nd ed. Prentice-Hall, Upper Saddle River.

[21]

The self-organizing map. Proceedings of the IEEE. v78. 1464-1480.

[22]

Kurniawan, F., Rehman, A., Mohamad, D., & Shamsudin, S. M. (2009). Self organizing feature maps with improved segmentation to identify touching of adjacent characters in handwritten words. In Ninth international conference on hybrid intelligent systems (pp. 475-480). Shenyang.

Digital Library

[23]

Lacerda, E. B., & Mello, C. A. B. (2011). Segmentation of touching handwritten digits using self-organizing maps. In 23rd IEEE international conference on tools with artificial intelligence (pp. 134-137). Boca Raton.

Digital Library

[24]

Thinning methodologies: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. v14. 869-885.

[25]

Fast and robust skew estimation of scanned documents through background area information. Pattern Recognition Letters. v31. 1403-1411.

Digital Library

[26]

Handwritten digit recognition by means of a holographic associative memory. Expert Systems with Applications. v15. 399-403.

[27]

Thresholding images of historical documents using a tsallis-entropy based algorithm. Journal of Software. v3. 29-36.

[28]

Neves, R. F. P., Lopes Filho, A. N. G., Mello, C. A. B., & Zanchettin, C., 2011. A svm based off-line digit recognizer. In 24th IEEE international conference on systems, man and cybernetics (pp. 510-515). Anchorage.

[29]

NIST. (1995). NIST special database 19. Handprinted forms and characters database.

[30]

. Executive briefing, 1997.IEEE Computer Society, Los Alamitos.

[31]

Oliveira, L. S. (1999). Automatic processing of handwritten digits. Technical report III PUC-PR Curitiba.

[32]

Touching numeral segmentation using water reservoir concept. Pattern Recognition Letters. v24. 261-272.

[33]

Algorithms for image processing and computer vision. John Wiley and Sons, New York.

[34]

On-line and off-line handwriting recognition: A comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. v22. 63-84.

[35]

Handwritten digit segmentation: A comparative study. International Journal on Document Analysis and Recognition (IJDAR). v16. 127-137.

[36]

Roe, E., & Mello, C. A. B. (2009). Simulating inertial and centripetal forces for segmentation of overlapped handwritten digits. In IEEE conference on systems, man and cybernetics (pp. 149-153). San Antonio.

[37]

Rui, M., Jie, D., Yunhua, G., & Yunyang, Y. (2009). An improved drop-fall algorithm based on backround analysis for handwritten digits segmentation. In Global congress on intelligent systems (pp. 374-378). Xiamen.

[38]

Artificial intelligence: A modern approach. 3rd ed. Prentice-Hall, Upper Saddle River.

[39]

A survey on methods and strategies on touched characters segmentation. International Journal of Research and Reviews in Computer Science. v1. 103-114.

[40]

Region growing based segmentation algorithm for typewritten and handwritten text recognition. Applied Soft Computing. v9. 608-617.

[41]

Automatic line and word segmentation applied to densely line-skewed historical handwritten document images. Integrated Computer-Aided Engineering. v11. 125-142.

[42]

Word segmentation of handwritten text using supervised classification techniques. Applied Soft Computing. v7. 71-88.

[43]

Suwa, M. (2005). Segmentation of connected handwritten numerals by graph representation. In Eighth international conference on document analysis and recognition (Vol. 2, pp. 750-754). Seoul.

Digital Library

[44]

Feature extraction methods for character recognition a survey. Pattern Recognition. v29. 641-662.

[45]

The nature of statistical learning. 2nd ed. Springer, New York.

[46]

Segment confidence-based binary segmentation (scbs) for cursive handwritten words. Expert Systems with Applications. v38. 11167-11175.

Digital Library

[47]

Vesanto, J., Himberg, J., Alhoniemi, E., & Parhankangas, J. (1999). Self-organizing map in matlab: The som toolbox. In Matlab DSP conference, Nov. 1999 (pp. 35-40). Espoo.

[48]

Wang, X., Govindaraju, V., & Srihari, S. (1998). Holistic recognition of touching digits. In Sixth international workshop on frontiers in handwriting recognition (pp. 295-303). Daejeon.

[49]

Inertial and big drop fall algorithm. International Journal of Information Technology. v12. 39-48.

[50]

Reconstruction of broken handwritten digits based on structured morphological features. Pattern Recognition. v34. 235-254.

Cited By

Schwedersky Bde Oliveira BAlbertazzi AFlesch R(2022)Impact damage characterization in CFRP samples with self-organizing maps applied to lock-in thermography and square-pulse shearography imagesExpert Systems with Applications: An International Journal10.1016/j.eswa.2021.116297192:COnline publication date: 15-Apr-2022
https://dl.acm.org/doi/10.1016/j.eswa.2021.116297
Vukovi VArizanovi B(2017)Efficient character segmentation approach for machine-typed documentsExpert Systems with Applications: An International Journal10.1016/j.eswa.2017.03.02780:C(210-231)Online publication date: 1-Sep-2017
https://dl.acm.org/doi/10.1016/j.eswa.2017.03.027
Ortega-Zamorano FMolina-Cabello MLópez-Rubio EPalomo E(2016)Smart motion detection sensor based on video processing using self-organizing mapsExpert Systems with Applications: An International Journal10.1016/j.eswa.2016.08.01064:C(476-489)Online publication date: 1-Dec-2016
https://dl.acm.org/doi/10.1016/j.eswa.2016.08.010
Show More Cited By

Segmentation of connected handwritten digits using Self-Organizing Maps
1. Applied computing
  1. Document management and text processing
    1. Document capture
2. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
  2. Machine learning
    1. Learning paradigms
      1. Supervised learning

Recommendations

Segmentation of Touching Handwritten Digits Using Self-Organizing Maps
ICTAI '11: Proceedings of the 2011 IEEE 23rd International Conference on Tools with Artificial Intelligence

This paper presents a new algorithm for segmentation of touching handwritten digits. The proposal is divided into two parts: the selection of feature points which is made after the application of skeletonization, and the use of Self-Organizing Maps to ...
Multiagents to Separating Handwritten Connected Digits

This paper addresses an important and vital problem within the general area of character recognition, namely separating connected digits in handwritten numerals. The basic idea is employing multiagents to handle this problem. Our approach is mainly ...
Segmentation of english Offline handwritten cursive scripts using a feedforward neural network

In the present paper, we used the Pixel Plot and Trace and Re-plot and Re-trace (PPTRPRT) technique for English offline handwritten curve scripts and leads. Unlike other approaches, the PPTRPRT technique prioritizes segmentation of words and characters. ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Expert Systems with Applications: An International Journal

Expert Systems with Applications: An International Journal Volume 40, Issue 15

November, 2013

435 pages

ISSN:0957-4174

Issue’s Table of Contents

Copyright © Elsevier Ltd © 2013.

Publisher

Pergamon Press, Inc.

United States

Publication History

Published: 01 November 2013

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 21 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Schwedersky Bde Oliveira BAlbertazzi AFlesch R(2022)Impact damage characterization in CFRP samples with self-organizing maps applied to lock-in thermography and square-pulse shearography imagesExpert Systems with Applications: An International Journal10.1016/j.eswa.2021.116297192:COnline publication date: 15-Apr-2022
https://dl.acm.org/doi/10.1016/j.eswa.2021.116297
Vukovi VArizanovi B(2017)Efficient character segmentation approach for machine-typed documentsExpert Systems with Applications: An International Journal10.1016/j.eswa.2017.03.02780:C(210-231)Online publication date: 1-Sep-2017
https://dl.acm.org/doi/10.1016/j.eswa.2017.03.027
Ortega-Zamorano FMolina-Cabello MLópez-Rubio EPalomo E(2016)Smart motion detection sensor based on video processing using self-organizing mapsExpert Systems with Applications: An International Journal10.1016/j.eswa.2016.08.01064:C(476-489)Online publication date: 1-Dec-2016
https://dl.acm.org/doi/10.1016/j.eswa.2016.08.010
Lopes Filho AMello CVanoirbeek CGenevès P(2015)Segmentation of Overlapping Digits through the Emulation of a Hypothetical Ball and Physical ForcesProceedings of the 2015 ACM Symposium on Document Engineering10.1145/2682571.2797080(223-226)Online publication date: 8-Sep-2015
https://dl.acm.org/doi/10.1145/2682571.2797080

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents