A novel statistical feature extraction method for textual images: Optical font recognition

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

The binary image is essential to image formats where the textual image is the best example of the binary image representation. Feature extraction is a fundamental process in pattern recognition. In this regard, pattern recognition studies involve document analysis techniques. Optical font recognition is among the pattern recognition techniques that are becoming popular today. In this paper, we propose an enhanced global feature extraction method based on the on statistical analysis of the behavior of edge pixels in binary images. A novel method in feature extraction for binary images has been proposed whereby the behavior of the edge pixels between a white background and a black pattern in a binary image captures information about the properties of the pattern. The proposed method is tested on an Arabic calligraphic script image for an optical font recognition application. To evaluate the performance of our proposed method, we compared it with a gray-level co occurrence matrix (GLCM). We classified the features using a multilayer artificial immune system, a Bayesian network, decision table rules, a decision tree, and a multilayer network to identify which approach is most suitable for our proposed method. The results of the experiments show that the proposed method with a decision tree classifier can boost the overall performance of optical font recognition.

Original languageEnglish
Pages (from-to)5470-5477
Number of pages8
JournalExpert Systems with Applications
Volume39
Issue number5
DOIs
Publication statusPublished - Apr 2012

Fingerprint

Binary images
Feature extraction
Pattern recognition
Decision trees
Multilayers
Pixels
Decision tables
Immune system
Bayesian networks
Statistical methods
Classifiers
Experiments

Keywords

  • Classification
  • Font recognition
  • Global analysis feature extraction
  • Gray level co-occurrence matrix
  • Statistical feature extraction

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Engineering(all)

Cite this

@article{876903e1747c480ea6e7e8d02f413097,
title = "A novel statistical feature extraction method for textual images: Optical font recognition",
abstract = "The binary image is essential to image formats where the textual image is the best example of the binary image representation. Feature extraction is a fundamental process in pattern recognition. In this regard, pattern recognition studies involve document analysis techniques. Optical font recognition is among the pattern recognition techniques that are becoming popular today. In this paper, we propose an enhanced global feature extraction method based on the on statistical analysis of the behavior of edge pixels in binary images. A novel method in feature extraction for binary images has been proposed whereby the behavior of the edge pixels between a white background and a black pattern in a binary image captures information about the properties of the pattern. The proposed method is tested on an Arabic calligraphic script image for an optical font recognition application. To evaluate the performance of our proposed method, we compared it with a gray-level co occurrence matrix (GLCM). We classified the features using a multilayer artificial immune system, a Bayesian network, decision table rules, a decision tree, and a multilayer network to identify which approach is most suitable for our proposed method. The results of the experiments show that the proposed method with a decision tree classifier can boost the overall performance of optical font recognition.",
keywords = "Classification, Font recognition, Global analysis feature extraction, Gray level co-occurrence matrix, Statistical feature extraction",
author = "Bilal Bataineh and {Sheikh Abdullah}, {Siti Norul Huda} and Khairuddin Omar",
year = "2012",
month = "4",
doi = "10.1016/j.eswa.2011.11.078",
language = "English",
volume = "39",
pages = "5470--5477",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - A novel statistical feature extraction method for textual images

T2 - Optical font recognition

AU - Bataineh, Bilal

AU - Sheikh Abdullah, Siti Norul Huda

AU - Omar, Khairuddin

PY - 2012/4

Y1 - 2012/4

N2 - The binary image is essential to image formats where the textual image is the best example of the binary image representation. Feature extraction is a fundamental process in pattern recognition. In this regard, pattern recognition studies involve document analysis techniques. Optical font recognition is among the pattern recognition techniques that are becoming popular today. In this paper, we propose an enhanced global feature extraction method based on the on statistical analysis of the behavior of edge pixels in binary images. A novel method in feature extraction for binary images has been proposed whereby the behavior of the edge pixels between a white background and a black pattern in a binary image captures information about the properties of the pattern. The proposed method is tested on an Arabic calligraphic script image for an optical font recognition application. To evaluate the performance of our proposed method, we compared it with a gray-level co occurrence matrix (GLCM). We classified the features using a multilayer artificial immune system, a Bayesian network, decision table rules, a decision tree, and a multilayer network to identify which approach is most suitable for our proposed method. The results of the experiments show that the proposed method with a decision tree classifier can boost the overall performance of optical font recognition.

AB - The binary image is essential to image formats where the textual image is the best example of the binary image representation. Feature extraction is a fundamental process in pattern recognition. In this regard, pattern recognition studies involve document analysis techniques. Optical font recognition is among the pattern recognition techniques that are becoming popular today. In this paper, we propose an enhanced global feature extraction method based on the on statistical analysis of the behavior of edge pixels in binary images. A novel method in feature extraction for binary images has been proposed whereby the behavior of the edge pixels between a white background and a black pattern in a binary image captures information about the properties of the pattern. The proposed method is tested on an Arabic calligraphic script image for an optical font recognition application. To evaluate the performance of our proposed method, we compared it with a gray-level co occurrence matrix (GLCM). We classified the features using a multilayer artificial immune system, a Bayesian network, decision table rules, a decision tree, and a multilayer network to identify which approach is most suitable for our proposed method. The results of the experiments show that the proposed method with a decision tree classifier can boost the overall performance of optical font recognition.

KW - Classification

KW - Font recognition

KW - Global analysis feature extraction

KW - Gray level co-occurrence matrix

KW - Statistical feature extraction

UR - http://www.scopus.com/inward/record.url?scp=84855865346&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855865346&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2011.11.078

DO - 10.1016/j.eswa.2011.11.078

M3 - Article

AN - SCOPUS:84855865346

VL - 39

SP - 5470

EP - 5477

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 5

ER -