Enhancement of Moment Invariants calculation for Arabic Handwriting recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Moment Invariant (MI) has been frequently used as feature for shape recognition. These features are invariant to several deformations such as rotation, scaling and translation. However it is sensitive to distortions that primarily affect the 'centre of gravity' of the image. Images of an Arabic Word might have different centroid due to the fact that it might be written using different Handwriting styles. In this paper we examine the effect of replacing the image centroid with the center of image as the reference point in Moment Invariant (MI). The new descriptors set was tested to recognize Arabic Words based on IFN/ENIT Database that consisting of 26459 words written by 411 different writers. The Back Propagation Neural Network was used as the classifier. Experiment results had shown that by using the new descriptors the average recognition accuracy has increased by 18.38%.

Original languageEnglish
Title of host publicationProceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011
Pages83-86
Number of pages4
Volume1
DOIs
Publication statusPublished - 2011
Event2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011 - Putrajaya
Duration: 28 Jun 201129 Jun 2011

Other

Other2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011
CityPutrajaya
Period28/6/1129/6/11

Fingerprint

Backpropagation
Gravitation
Classifiers
Neural networks
Experiments

Keywords

  • Feature Extraction
  • Handwritten Arabic Word Recognition
  • MLP Neural Networks
  • Moment Invariant

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Cite this

Abdullah, T. N., Omar, K., & Nasrudin, M. F. (2011). Enhancement of Moment Invariants calculation for Arabic Handwriting recognition. In Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011 (Vol. 1, pp. 83-86). [5976916] https://doi.org/10.1109/ICPAIR.2011.5976916

Enhancement of Moment Invariants calculation for Arabic Handwriting recognition. / Abdullah, Twana N.; Omar, Khairuddin; Nasrudin, Mohammad Faidzul.

Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011. Vol. 1 2011. p. 83-86 5976916.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abdullah, TN, Omar, K & Nasrudin, MF 2011, Enhancement of Moment Invariants calculation for Arabic Handwriting recognition. in Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011. vol. 1, 5976916, pp. 83-86, 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011, Putrajaya, 28/6/11. https://doi.org/10.1109/ICPAIR.2011.5976916
Abdullah TN, Omar K, Nasrudin MF. Enhancement of Moment Invariants calculation for Arabic Handwriting recognition. In Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011. Vol. 1. 2011. p. 83-86. 5976916 https://doi.org/10.1109/ICPAIR.2011.5976916
Abdullah, Twana N. ; Omar, Khairuddin ; Nasrudin, Mohammad Faidzul. / Enhancement of Moment Invariants calculation for Arabic Handwriting recognition. Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011. Vol. 1 2011. pp. 83-86
@inproceedings{68fd5a82b70047db949a1dc15062db1e,
title = "Enhancement of Moment Invariants calculation for Arabic Handwriting recognition",
abstract = "Moment Invariant (MI) has been frequently used as feature for shape recognition. These features are invariant to several deformations such as rotation, scaling and translation. However it is sensitive to distortions that primarily affect the 'centre of gravity' of the image. Images of an Arabic Word might have different centroid due to the fact that it might be written using different Handwriting styles. In this paper we examine the effect of replacing the image centroid with the center of image as the reference point in Moment Invariant (MI). The new descriptors set was tested to recognize Arabic Words based on IFN/ENIT Database that consisting of 26459 words written by 411 different writers. The Back Propagation Neural Network was used as the classifier. Experiment results had shown that by using the new descriptors the average recognition accuracy has increased by 18.38{\%}.",
keywords = "Feature Extraction, Handwritten Arabic Word Recognition, MLP Neural Networks, Moment Invariant",
author = "Abdullah, {Twana N.} and Khairuddin Omar and Nasrudin, {Mohammad Faidzul}",
year = "2011",
doi = "10.1109/ICPAIR.2011.5976916",
language = "English",
isbn = "9781612844046",
volume = "1",
pages = "83--86",
booktitle = "Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011",

}

TY - GEN

T1 - Enhancement of Moment Invariants calculation for Arabic Handwriting recognition

AU - Abdullah, Twana N.

AU - Omar, Khairuddin

AU - Nasrudin, Mohammad Faidzul

PY - 2011

Y1 - 2011

N2 - Moment Invariant (MI) has been frequently used as feature for shape recognition. These features are invariant to several deformations such as rotation, scaling and translation. However it is sensitive to distortions that primarily affect the 'centre of gravity' of the image. Images of an Arabic Word might have different centroid due to the fact that it might be written using different Handwriting styles. In this paper we examine the effect of replacing the image centroid with the center of image as the reference point in Moment Invariant (MI). The new descriptors set was tested to recognize Arabic Words based on IFN/ENIT Database that consisting of 26459 words written by 411 different writers. The Back Propagation Neural Network was used as the classifier. Experiment results had shown that by using the new descriptors the average recognition accuracy has increased by 18.38%.

AB - Moment Invariant (MI) has been frequently used as feature for shape recognition. These features are invariant to several deformations such as rotation, scaling and translation. However it is sensitive to distortions that primarily affect the 'centre of gravity' of the image. Images of an Arabic Word might have different centroid due to the fact that it might be written using different Handwriting styles. In this paper we examine the effect of replacing the image centroid with the center of image as the reference point in Moment Invariant (MI). The new descriptors set was tested to recognize Arabic Words based on IFN/ENIT Database that consisting of 26459 words written by 411 different writers. The Back Propagation Neural Network was used as the classifier. Experiment results had shown that by using the new descriptors the average recognition accuracy has increased by 18.38%.

KW - Feature Extraction

KW - Handwritten Arabic Word Recognition

KW - MLP Neural Networks

KW - Moment Invariant

UR - http://www.scopus.com/inward/record.url?scp=80052220473&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052220473&partnerID=8YFLogxK

U2 - 10.1109/ICPAIR.2011.5976916

DO - 10.1109/ICPAIR.2011.5976916

M3 - Conference contribution

SN - 9781612844046

VL - 1

SP - 83

EP - 86

BT - Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011

ER -