article

Offline handwritten Amharic word recognition

Authors:

Yaregal Assabie,

Josef BigunAuthors Info & Claims

Pattern Recognition Letters, Volume 32, Issue 8

Pages 1089 - 1099

https://doi.org/10.1016/j.patrec.2011.02.007

Published: 01 June 2011 Publication History

Abstract

This paper describes two approaches for Amharic word recognition in unconstrained handwritten text using HMMs. The first approach builds word models from concatenated features of constituent characters and in the second method HMMs of constituent characters are concatenated to form word model. In both cases, the features used for training and recognition are a set of primitive strokes and their spatial relationships. The recognition system does not require segmentation of characters but requires text line detection and extraction of structural features, which is done by making use of direction field tensor. The performance of the recognition system is tested by a dataset of unconstrained handwritten documents collected from various sources, and promising results are obtained.

References

[1]

An overview of character recognition focused on off-line handwriting. IEEE Trans. Systems Man Cybernet. v31 i2. 216-233.

Digital Library

[2]

Multifont size-resilient recognition system for Ethiopic script. Internat. J. Document Anal. Recognition. v10 i2. 85-100.

Digital Library

[3]

Assabie, Y., Bigun, J., 2008. Lexicon-based offline recognition of Amharic words in unconstrained handwritten text. In: The 19th Internat. Conf. Pattern Recognition (ICPR2008), December 8-11, Tampa, Florida, USA. IEEE.

[4]

Bar-Yosef, I., Hagbi, N., Kedem, K., Dinstein, I., 2009. Line segmentation for degraded handwritten historical documents. In: Proceedings of the 10th Internat. Conf. Document Analysis and Recognition (ICDAR2009), Barcelona, Spain, pp. 1161-1165.

Digital Library

[5]

Gaussian derivative model for edge enhancement. Pattern Recognition. v27 i11. 1451-1461.

[6]

Vision with Direction. Springer, Heidelberg.

[7]

Optimal orientation detection of linear symmetry. In: First International Conference on Computer Vision, ICCV, London, June 8-11, IEEE Computer Society. pp. 433-438.

[8]

Recognition by symmetry derivatives and the generalized structure tensor. IEEE TPAMI. v26 i2. 1590-1605.

Digital Library

[9]

Bunke, H., 2003. Recognition of cursive Roman handwriting - past, present and future. In: Proc. 7th Internat. Conf. Document Analysis and Recognition, Edinburgh, pp. 448-459.

Digital Library

[10]

Character Recognition Systems. John Wiley, New York.

[11]

An HMM-based approach for off-line unconstrained handwritten word modeling and recognition. IEEE TPAMI. v21 i8. 752-760.

Digital Library

[12]

Forty years of research in character and document recognition - An industrial perspective. Pattern Recognition. v41 i8. 2435-2446.

Digital Library

[13]

African language literatures: An introduction to the literary history of Sub-Saharan Africa. Three Continents Press, Washington.

[14]

Ethnologue: Languages of the world. fifteenth ed. SIL International, Dallas.

[15]

Huang, C., Srihari, S., 2008. Word segmentation of off-line handwritten documents. In: Proc. Document Recognition and Retrieval XV, IST/SPIE Annual Symposium, vol. 6815.

[16]

Statistical pattern recognition: A review. IEEE TPAMI. v22 i1. 4-37.

Digital Library

[17]

Recognising handwritten Arabic manuscripts using a single hidden Markov model. Pattern Recognition Lett. v24 i3. 2235-2242.

Digital Library

[18]

Kim, K., Kim, D., Aggarwal, J., 1998. Feature extraction of edge by directional computation of gray-scale variation. In: Proc. 14th Internat. Conf. on Pattern Recognition (ICPR'98), vol. 2, pp. 1022-1027.

Digital Library

[19]

Koerich, A.L., Leydier, Y., Sabourin, R., Suen, C.Y., 2002. A hybrid large vocabulary handwritten word recognition system using neural networks with hidden Markov models. In: Proc. IWFHR2002, pp. 99-104.

Digital Library

[20]

Koerich, A.L., Sabourin, R., Suen, C.Y., 2003. Lexicon-driven HMM decoding for large vocabulary handwriting recognition with multiple character models. 6, 126-144.

[21]

Li, Y., Zheng, Y., Doermann, D., Jaeger, S., 2006. A new algorithm for detecting text line in handwritten documents. In: Proc. 10th IWFHR, La Baule, France, pp. 35-40.

[22]

Classification and Learning Methods for Character Recognition: Advances and Remaining Problems. Springer, Berlin.

[23]

Handwriting Recognition: Soft Computing and Probabilistic Approaches. Springer, Berlin.

[24]

Offline Arabic handwritten word recognition: A survey. IEEE TPAMI. v28 i5. 712-724.

Digital Library

[25]

Text line and word segmentation of handwritten documents. Pattern Recognition. v42 i12. 3169-3183.

Digital Library

[26]

The role of holistic paradigms in handwritten word recognition. IEEE TPAMI. v23 i2. 149-164.

Digital Library

[27]

Artificial neural networks for document analysis and recognition. IEEE TPAMI. v27 i1. 23-35.

Digital Library

[28]

Meshesha, M., Jawahar, C.V., 2005. Recognition of printed Amharic documents. In: Internat. Conf. Document Analysis and Recognition (ICDAR), pp. 784-788.

Digital Library

[29]

Historical review of OCR research and development. Proc. IEEE. v80 i7. 1029-1058.

[30]

On-line and off-line handwriting recognition: A comprehensive survey. IEEE TPAMI. v22 i1. 63-84.

Digital Library

[31]

A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE. v77 i2. 257-286.

[32]

An introduction to hidden Markov models. IEEE Acoust. Speech Signal Process. Mag. v3 i1. 4-16.

[33]

Holistic cursive word recognition based on perceptual features. Pattern Recognition Lett. v28 i13. 1600-1609.

Digital Library

[34]

Selvi, S., Indira, K., 2005. A novel character segmentation algorithm for offline handwritten character recognition. In: Proc. 10th IWFHR, Mysore, India, pp. 462-468.

[35]

Offline handwritten Chinese character recognition by radical decomposition. ACM Trans. Asian Lang. Inform. Process. v2 i1. 27-48.

Digital Library

[36]

High-performance reading machines. Proc. IEEE. v80 i7. 1120-1132.

[37]

Machine-printed Japanese document recognition. Pattern Recognition. v80 i8. 1301-1313.

[38]

Suen, C.Y., Mori, S., Kim, S.H., Leung, C.H., 2003. Analysis and recognition of Asian scripts - The state of the art. In: Proc. 7th Internat. Conf. Document Analysis and Recognition, Edinburgh, pp. 866-878.

Digital Library

[39]

Tan, T., Sullivan, G., Baker, K., 1996. Efficient image gradient-based object localization and recognition. In: Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR'96), pp. 397-402.

Digital Library

[40]

Eigen-deformations for elastic matching based handwritten character recognition. Pattern Recognition. v36 i9. 2031-2040.

[41]

Offline recognition of unconstrained handwritten texts using HMMs and statistical language models. IEEE TPAMI. v26 i6. 709-720.

Digital Library

[42]

The HTK Book. Cambridge University Engineering Department, Cambridge.

Cited By

Belay BGuyon IMengiste TTilahun BLiwicki MTegegne TEgele R(2024)A Historical Handwritten Dataset for Ethiopic OCR with Baseline Models and Human-Level PerformanceDocument Analysis and Recognition - ICDAR 202410.1007/978-3-031-70543-4_2(23-38)Online publication date: 30-Aug-2024
https://dl.acm.org/doi/10.1007/978-3-031-70543-4_2
Gondere MSchmidt-Thieme LSharma DScholz R(2022)Multi-script handwritten digit recognition using multi-task learningJournal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology10.3233/JIFS-21223343:1(355-364)Online publication date: 1-Jan-2022
https://dl.acm.org/doi/10.3233/JIFS-212233
Hassen MAssabie YKacprzyk JLaurent DChbeir R(2012)Recognition of Ethiopic braille charactersProceedings of the International Conference on Management of Emergent Digital EcoSystems10.1145/2457276.2457304(158-165)Online publication date: 28-Oct-2012
https://dl.acm.org/doi/10.1145/2457276.2457304

Index Terms

Offline handwritten Amharic word recognition
1. Applied computing
  1. Document management and text processing
    1. Document capture
      1. Optical character recognition
2. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
        Supervised learning by classification
    2. Machine learning algorithms
      1. Feature selection

Index terms have been assigned to the content through auto-classification.

Recommendations

Offline arabic handwritten text recognition: A Survey

Research in offline Arabic handwriting recognition has increased considerably in the past few years. This is evident from the numerous research results published recently in major journals and conferences in the area of handwriting recognition. Features ...
Indic script family and its offline handwriting recognition for characters/digits and words: a comprehensive survey
Abstract
Handwriting recognition has become an active area of research in pattern recognition and machine learning in recent years. Handwriting recognition systems have a variety of applications ranging from digital character conversion to signboard ...
Two template matching approaches to Arabic, Amharic and Latin isolated characters recognition

With the establishment of commercial OCR systems for Latin text, recent research efforts have been directed at the design of recognition systems for non-Latin scripts, such as Japanese, Cyrillic, Chinese, Hindi, Tibetan, and in particular Arabic. The ...

Comments

Information & Contributors

Information

Published In

cover image Pattern Recognition Letters

Pattern Recognition Letters Volume 32, Issue 8

June, 2011

142 pages

ISSN:0167-8655

Issue’s Table of Contents

Copyright © Elsevier B.V. © 2011.

Publisher

Elsevier Science Inc.

United States

Publication History

Published: 01 June 2011

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 15 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Belay BGuyon IMengiste TTilahun BLiwicki MTegegne TEgele R(2024)A Historical Handwritten Dataset for Ethiopic OCR with Baseline Models and Human-Level PerformanceDocument Analysis and Recognition - ICDAR 202410.1007/978-3-031-70543-4_2(23-38)Online publication date: 30-Aug-2024
https://dl.acm.org/doi/10.1007/978-3-031-70543-4_2
Gondere MSchmidt-Thieme LSharma DScholz R(2022)Multi-script handwritten digit recognition using multi-task learningJournal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology10.3233/JIFS-21223343:1(355-364)Online publication date: 1-Jan-2022
https://dl.acm.org/doi/10.3233/JIFS-212233
Hassen MAssabie YKacprzyk JLaurent DChbeir R(2012)Recognition of Ethiopic braille charactersProceedings of the International Conference on Management of Emergent Digital EcoSystems10.1145/2457276.2457304(158-165)Online publication date: 28-Oct-2012
https://dl.acm.org/doi/10.1145/2457276.2457304

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 Issue’s Table of Contents