Efficient postprocessing algorithms for error correction in handwritten Hangul address and human name recognition

Seong Whan Lee, Eun Soon Kim

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

In this paper, we propose efficient postprocessing algorithms for error correction in handwritten Hangul (Korean script) address and human name recognition. As the load on the character recognizer for the recognition of the administrative district part of addresses was reduced by restricting the number of candidate characters to be matched by using an address lexicon, the processing speed and recognition rate were greatly improved. Also, as the misrecognition results from the character recognizer were corrected by efficient postprocessing algorithms based on backtracking, a high recognition rate of more than 98% could be obtained for the administrative district part of input addresses. For the recognition of human name part, misrecognition could be effectively corrected by combining the a priori probability and the confusion probability of each character which composes human names.

Original languageEnglish
Pages (from-to)1631-1640
Number of pages10
JournalPattern Recognition
Volume27
Issue number12
DOIs
Publication statusPublished - 1994 Dec 1
Externally publishedYes

Fingerprint

Error correction
Processing

Keywords

  • Address recognition
  • Error correction
  • Handwritten character recognition
  • Hangul recognition
  • Human name recognition
  • Postprocessing algorithm

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Efficient postprocessing algorithms for error correction in handwritten Hangul address and human name recognition. / Lee, Seong Whan; Kim, Eun Soon.

In: Pattern Recognition, Vol. 27, No. 12, 01.12.1994, p. 1631-1640.

Research output: Contribution to journalArticle

@article{6d4ce5b1d1c9469d98ac7ae1dc14507e,
title = "Efficient postprocessing algorithms for error correction in handwritten Hangul address and human name recognition",
abstract = "In this paper, we propose efficient postprocessing algorithms for error correction in handwritten Hangul (Korean script) address and human name recognition. As the load on the character recognizer for the recognition of the administrative district part of addresses was reduced by restricting the number of candidate characters to be matched by using an address lexicon, the processing speed and recognition rate were greatly improved. Also, as the misrecognition results from the character recognizer were corrected by efficient postprocessing algorithms based on backtracking, a high recognition rate of more than 98{\%} could be obtained for the administrative district part of input addresses. For the recognition of human name part, misrecognition could be effectively corrected by combining the a priori probability and the confusion probability of each character which composes human names.",
keywords = "Address recognition, Error correction, Handwritten character recognition, Hangul recognition, Human name recognition, Postprocessing algorithm",
author = "Lee, {Seong Whan} and Kim, {Eun Soon}",
year = "1994",
month = "12",
day = "1",
doi = "10.1016/0031-3203(94)90082-5",
language = "English",
volume = "27",
pages = "1631--1640",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "12",

}

TY - JOUR

T1 - Efficient postprocessing algorithms for error correction in handwritten Hangul address and human name recognition

AU - Lee, Seong Whan

AU - Kim, Eun Soon

PY - 1994/12/1

Y1 - 1994/12/1

N2 - In this paper, we propose efficient postprocessing algorithms for error correction in handwritten Hangul (Korean script) address and human name recognition. As the load on the character recognizer for the recognition of the administrative district part of addresses was reduced by restricting the number of candidate characters to be matched by using an address lexicon, the processing speed and recognition rate were greatly improved. Also, as the misrecognition results from the character recognizer were corrected by efficient postprocessing algorithms based on backtracking, a high recognition rate of more than 98% could be obtained for the administrative district part of input addresses. For the recognition of human name part, misrecognition could be effectively corrected by combining the a priori probability and the confusion probability of each character which composes human names.

AB - In this paper, we propose efficient postprocessing algorithms for error correction in handwritten Hangul (Korean script) address and human name recognition. As the load on the character recognizer for the recognition of the administrative district part of addresses was reduced by restricting the number of candidate characters to be matched by using an address lexicon, the processing speed and recognition rate were greatly improved. Also, as the misrecognition results from the character recognizer were corrected by efficient postprocessing algorithms based on backtracking, a high recognition rate of more than 98% could be obtained for the administrative district part of input addresses. For the recognition of human name part, misrecognition could be effectively corrected by combining the a priori probability and the confusion probability of each character which composes human names.

KW - Address recognition

KW - Error correction

KW - Handwritten character recognition

KW - Hangul recognition

KW - Human name recognition

KW - Postprocessing algorithm

UR - http://www.scopus.com/inward/record.url?scp=0028728453&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028728453&partnerID=8YFLogxK

U2 - 10.1016/0031-3203(94)90082-5

DO - 10.1016/0031-3203(94)90082-5

M3 - Article

AN - SCOPUS:0028728453

VL - 27

SP - 1631

EP - 1640

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 12

ER -