New primitives to reduce the effect of noise for handwritten features extraction

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

5 Citations (Scopus)

Abstract

A method for feature extraction for handwritten OCR system is presented. In order to reduce the effect of the noise which is either an original noise or obtained as a result of the preprocessing stages, there is a need to develop a feature extraction method invariant to the expected distortions, and less dependent on the locations of high probable appearance of noise and distortion. This method depends only on the two primitive features: straight lines and curves. A chain code has been built from the thinned shape of the character. Two rules have been introduced to cut this chain code into small segments. From each segment one feature is defined and for each input character, a feature vector will be built. The prototype system was tested for alphanumeric characters and the results were satisfactory.

Original languageEnglish
Title of host publicationIEEE Region 10 Annual International Conference, Proceedings/TENCON
Volume2
Publication statusPublished - 2000
Externally publishedYes
Event2000 TENCON Proceedings - Kuala Lumpur, Malaysia
Duration: 24 Sep 200027 Sep 2000

Other

Other2000 TENCON Proceedings
CityKuala Lumpur, Malaysia
Period24/9/0027/9/00

Fingerprint

Feature extraction
Optical character recognition

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Zeki, A. M., & Zakaria, M. S. (2000). New primitives to reduce the effect of noise for handwritten features extraction. In IEEE Region 10 Annual International Conference, Proceedings/TENCON (Vol. 2)

New primitives to reduce the effect of noise for handwritten features extraction. / Zeki, Ahmed M.; Zakaria, Mohamad Shanudin.

IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. 2 2000.

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

Zeki, AM & Zakaria, MS 2000, New primitives to reduce the effect of noise for handwritten features extraction. in IEEE Region 10 Annual International Conference, Proceedings/TENCON. vol. 2, 2000 TENCON Proceedings, Kuala Lumpur, Malaysia, 24/9/00.
Zeki AM, Zakaria MS. New primitives to reduce the effect of noise for handwritten features extraction. In IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. 2. 2000
Zeki, Ahmed M. ; Zakaria, Mohamad Shanudin. / New primitives to reduce the effect of noise for handwritten features extraction. IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. 2 2000.
@inproceedings{0e4c3757c5684f3b9f3fcbedc2162577,
title = "New primitives to reduce the effect of noise for handwritten features extraction",
abstract = "A method for feature extraction for handwritten OCR system is presented. In order to reduce the effect of the noise which is either an original noise or obtained as a result of the preprocessing stages, there is a need to develop a feature extraction method invariant to the expected distortions, and less dependent on the locations of high probable appearance of noise and distortion. This method depends only on the two primitive features: straight lines and curves. A chain code has been built from the thinned shape of the character. Two rules have been introduced to cut this chain code into small segments. From each segment one feature is defined and for each input character, a feature vector will be built. The prototype system was tested for alphanumeric characters and the results were satisfactory.",
author = "Zeki, {Ahmed M.} and Zakaria, {Mohamad Shanudin}",
year = "2000",
language = "English",
volume = "2",
booktitle = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

}

TY - GEN

T1 - New primitives to reduce the effect of noise for handwritten features extraction

AU - Zeki, Ahmed M.

AU - Zakaria, Mohamad Shanudin

PY - 2000

Y1 - 2000

N2 - A method for feature extraction for handwritten OCR system is presented. In order to reduce the effect of the noise which is either an original noise or obtained as a result of the preprocessing stages, there is a need to develop a feature extraction method invariant to the expected distortions, and less dependent on the locations of high probable appearance of noise and distortion. This method depends only on the two primitive features: straight lines and curves. A chain code has been built from the thinned shape of the character. Two rules have been introduced to cut this chain code into small segments. From each segment one feature is defined and for each input character, a feature vector will be built. The prototype system was tested for alphanumeric characters and the results were satisfactory.

AB - A method for feature extraction for handwritten OCR system is presented. In order to reduce the effect of the noise which is either an original noise or obtained as a result of the preprocessing stages, there is a need to develop a feature extraction method invariant to the expected distortions, and less dependent on the locations of high probable appearance of noise and distortion. This method depends only on the two primitive features: straight lines and curves. A chain code has been built from the thinned shape of the character. Two rules have been introduced to cut this chain code into small segments. From each segment one feature is defined and for each input character, a feature vector will be built. The prototype system was tested for alphanumeric characters and the results were satisfactory.

UR - http://www.scopus.com/inward/record.url?scp=0034429517&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034429517&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034429517

VL - 2

BT - IEEE Region 10 Annual International Conference, Proceedings/TENCON

ER -