A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM

study case on Malay word recognition

Omar N. Al-Boeridi, S. M. Syed Ahmad, Johnny Siaw Paw Koh

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

An off-line handwriting recognition (OFHR) system is a computerized system that is capable of intelligently converting human handwritten data extracted from scanned paper documents into an equivalent text format. This paper studies a proposed OFHR for Malaysian bank cheques written in the Malay language. The proposed system comprised of three components, namely a character recognition system (CRS), a hybrid decision system and lexical word classification system. Two types of feature extraction techniques have been used in the system, namely statistical and geometrical. Experiments show that the statistical feature is reliable, accessible and offers results that are more accurate. The CRS in this system was implemented using two individual classifiers, namely an adaptive multilayer feed-forward back-propagation neural network and support vector machine. The results of this study are very promising and could generalize to the entire Malay lexical dictionary in future work toward scaled-up applications.

Original languageEnglish
Pages (from-to)1505-1513
Number of pages9
JournalNeural Computing and Applications
Volume26
Issue number6
DOIs
Publication statusPublished - 25 Aug 2015

Fingerprint

Character recognition
Glossaries
Backpropagation
Support vector machines
Feature extraction
Multilayers
Classifiers
Neural networks
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

@article{881cae92e37a414894408cfb915aba6b,
title = "A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: study case on Malay word recognition",
abstract = "An off-line handwriting recognition (OFHR) system is a computerized system that is capable of intelligently converting human handwritten data extracted from scanned paper documents into an equivalent text format. This paper studies a proposed OFHR for Malaysian bank cheques written in the Malay language. The proposed system comprised of three components, namely a character recognition system (CRS), a hybrid decision system and lexical word classification system. Two types of feature extraction techniques have been used in the system, namely statistical and geometrical. Experiments show that the statistical feature is reliable, accessible and offers results that are more accurate. The CRS in this system was implemented using two individual classifiers, namely an adaptive multilayer feed-forward back-propagation neural network and support vector machine. The results of this study are very promising and could generalize to the entire Malay lexical dictionary in future work toward scaled-up applications.",
author = "Al-Boeridi, {Omar N.} and {Syed Ahmad}, {S. M.} and Koh, {Johnny Siaw Paw}",
year = "2015",
month = "8",
day = "25",
doi = "10.1007/s00521-015-1824-0",
language = "English",
volume = "26",
pages = "1505--1513",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",
number = "6",

}

A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM : study case on Malay word recognition. / Al-Boeridi, Omar N.; Syed Ahmad, S. M.; Koh, Johnny Siaw Paw.

In: Neural Computing and Applications, Vol. 26, No. 6, 25.08.2015, p. 1505-1513.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM

T2 - study case on Malay word recognition

AU - Al-Boeridi, Omar N.

AU - Syed Ahmad, S. M.

AU - Koh, Johnny Siaw Paw

PY - 2015/8/25

Y1 - 2015/8/25

N2 - An off-line handwriting recognition (OFHR) system is a computerized system that is capable of intelligently converting human handwritten data extracted from scanned paper documents into an equivalent text format. This paper studies a proposed OFHR for Malaysian bank cheques written in the Malay language. The proposed system comprised of three components, namely a character recognition system (CRS), a hybrid decision system and lexical word classification system. Two types of feature extraction techniques have been used in the system, namely statistical and geometrical. Experiments show that the statistical feature is reliable, accessible and offers results that are more accurate. The CRS in this system was implemented using two individual classifiers, namely an adaptive multilayer feed-forward back-propagation neural network and support vector machine. The results of this study are very promising and could generalize to the entire Malay lexical dictionary in future work toward scaled-up applications.

AB - An off-line handwriting recognition (OFHR) system is a computerized system that is capable of intelligently converting human handwritten data extracted from scanned paper documents into an equivalent text format. This paper studies a proposed OFHR for Malaysian bank cheques written in the Malay language. The proposed system comprised of three components, namely a character recognition system (CRS), a hybrid decision system and lexical word classification system. Two types of feature extraction techniques have been used in the system, namely statistical and geometrical. Experiments show that the statistical feature is reliable, accessible and offers results that are more accurate. The CRS in this system was implemented using two individual classifiers, namely an adaptive multilayer feed-forward back-propagation neural network and support vector machine. The results of this study are very promising and could generalize to the entire Malay lexical dictionary in future work toward scaled-up applications.

UR - http://www.scopus.com/inward/record.url?scp=84937971328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937971328&partnerID=8YFLogxK

U2 - 10.1007/s00521-015-1824-0

DO - 10.1007/s00521-015-1824-0

M3 - Article

VL - 26

SP - 1505

EP - 1513

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 6

ER -