A new methodology for gray-scale character segmentation and recognition

Seong Whan Lee, Dong June Lee, Hee Seon Park

Research output: Contribution to journalArticle

91 Citations (Scopus)

Abstract

Generally speaking through the binarization of gray-scale images useful information for the segmentation of touched or overlapped characters may be lost in many cases. If we analyze grayscale images however specific topographic features and the variation of intensities can be observed in the character boundaries. We believe that such kinds of clues obtained from gray-scale images may work for efficient character segmentation and recognition. In this paper we propose a new methodology for character segmentation and recognition which makes the best use of the characteristics of grayscale images. In the proposed methodology the character segmentation regions are determined by using projection profiles and topographic features extracted from the gray-scale images. Then a nonlinear character segmentation path in each character segmentation region is found by using multi-stage graph search algorithm. Finally in order to confirm the nonlinear character segmentation paths and recognition results recognition-based segmentation method is adopted. Through the experiments with various kinds of printed documents it is convinced that the proposed methodology is very effective for the segmGntation and recognition of touched and overlapped characters.

Original languageEnglish
Pages (from-to)1045-1050
Number of pages6
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume18
Issue number10
DOIs
Publication statusPublished - 1996 Dec 1

Fingerprint

Segmentation
Methodology
Experiments
Region Segmentation
Graph Search
Character
Binarization
Path
Graph Algorithms
Search Algorithm
Projection
Experiment

Keywords

  • Character segmentation and recognition
  • Gray-scale character recognition
  • Multistage graph search
  • Recognition-based segmentation
  • Topographic feature

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

A new methodology for gray-scale character segmentation and recognition. / Lee, Seong Whan; Lee, Dong June; Park, Hee Seon.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No. 10, 01.12.1996, p. 1045-1050.

Research output: Contribution to journalArticle

@article{aa7f8aadbddb4007a185372f32d9d8c3,
title = "A new methodology for gray-scale character segmentation and recognition",
abstract = "Generally speaking through the binarization of gray-scale images useful information for the segmentation of touched or overlapped characters may be lost in many cases. If we analyze grayscale images however specific topographic features and the variation of intensities can be observed in the character boundaries. We believe that such kinds of clues obtained from gray-scale images may work for efficient character segmentation and recognition. In this paper we propose a new methodology for character segmentation and recognition which makes the best use of the characteristics of grayscale images. In the proposed methodology the character segmentation regions are determined by using projection profiles and topographic features extracted from the gray-scale images. Then a nonlinear character segmentation path in each character segmentation region is found by using multi-stage graph search algorithm. Finally in order to confirm the nonlinear character segmentation paths and recognition results recognition-based segmentation method is adopted. Through the experiments with various kinds of printed documents it is convinced that the proposed methodology is very effective for the segmGntation and recognition of touched and overlapped characters.",
keywords = "Character segmentation and recognition, Gray-scale character recognition, Multistage graph search, Recognition-based segmentation, Topographic feature",
author = "Lee, {Seong Whan} and Lee, {Dong June} and Park, {Hee Seon}",
year = "1996",
month = "12",
day = "1",
doi = "10.1109/34.541415",
language = "English",
volume = "18",
pages = "1045--1050",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "10",

}

TY - JOUR

T1 - A new methodology for gray-scale character segmentation and recognition

AU - Lee, Seong Whan

AU - Lee, Dong June

AU - Park, Hee Seon

PY - 1996/12/1

Y1 - 1996/12/1

N2 - Generally speaking through the binarization of gray-scale images useful information for the segmentation of touched or overlapped characters may be lost in many cases. If we analyze grayscale images however specific topographic features and the variation of intensities can be observed in the character boundaries. We believe that such kinds of clues obtained from gray-scale images may work for efficient character segmentation and recognition. In this paper we propose a new methodology for character segmentation and recognition which makes the best use of the characteristics of grayscale images. In the proposed methodology the character segmentation regions are determined by using projection profiles and topographic features extracted from the gray-scale images. Then a nonlinear character segmentation path in each character segmentation region is found by using multi-stage graph search algorithm. Finally in order to confirm the nonlinear character segmentation paths and recognition results recognition-based segmentation method is adopted. Through the experiments with various kinds of printed documents it is convinced that the proposed methodology is very effective for the segmGntation and recognition of touched and overlapped characters.

AB - Generally speaking through the binarization of gray-scale images useful information for the segmentation of touched or overlapped characters may be lost in many cases. If we analyze grayscale images however specific topographic features and the variation of intensities can be observed in the character boundaries. We believe that such kinds of clues obtained from gray-scale images may work for efficient character segmentation and recognition. In this paper we propose a new methodology for character segmentation and recognition which makes the best use of the characteristics of grayscale images. In the proposed methodology the character segmentation regions are determined by using projection profiles and topographic features extracted from the gray-scale images. Then a nonlinear character segmentation path in each character segmentation region is found by using multi-stage graph search algorithm. Finally in order to confirm the nonlinear character segmentation paths and recognition results recognition-based segmentation method is adopted. Through the experiments with various kinds of printed documents it is convinced that the proposed methodology is very effective for the segmGntation and recognition of touched and overlapped characters.

KW - Character segmentation and recognition

KW - Gray-scale character recognition

KW - Multistage graph search

KW - Recognition-based segmentation

KW - Topographic feature

UR - http://www.scopus.com/inward/record.url?scp=0030261113&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030261113&partnerID=8YFLogxK

U2 - 10.1109/34.541415

DO - 10.1109/34.541415

M3 - Article

VL - 18

SP - 1045

EP - 1050

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 10

ER -