Nonuniform slant correction for handwritten word recognition

Eiji Taira, Seiichi Uchida, Hiroaki Sakoe

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Slant correction is a preprocessing technique to improve segmentation and recognition accuracy for handwritten word recognition. All conventional slant correction techniques were performed by the estimation of the average slant angle and the shear transformation. In this paper, a nonuniform slant correction technique for handwritten word recognition is proposed where the slant correction problem is formulated as a global optimal estimation problem of the sequence of local slant angles. The optimal estimation is performed by a dynamic programming based algorithm. From experimental results it was shown that the present technique outperforms conventional uniform slant correction techniques.

Original languageEnglish
Pages (from-to)1247-1253
Number of pages7
JournalIEICE Transactions on Information and Systems
VolumeE87-D
Issue number5
Publication statusPublished - Jan 1 2004

Fingerprint

Dynamic programming

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

Nonuniform slant correction for handwritten word recognition. / Taira, Eiji; Uchida, Seiichi; Sakoe, Hiroaki.

In: IEICE Transactions on Information and Systems, Vol. E87-D, No. 5, 01.01.2004, p. 1247-1253.

Research output: Contribution to journalArticle

@article{d52983fd9ae7426b8b56d2d7bdedd5f0,
title = "Nonuniform slant correction for handwritten word recognition",
abstract = "Slant correction is a preprocessing technique to improve segmentation and recognition accuracy for handwritten word recognition. All conventional slant correction techniques were performed by the estimation of the average slant angle and the shear transformation. In this paper, a nonuniform slant correction technique for handwritten word recognition is proposed where the slant correction problem is formulated as a global optimal estimation problem of the sequence of local slant angles. The optimal estimation is performed by a dynamic programming based algorithm. From experimental results it was shown that the present technique outperforms conventional uniform slant correction techniques.",
author = "Eiji Taira and Seiichi Uchida and Hiroaki Sakoe",
year = "2004",
month = "1",
day = "1",
language = "English",
volume = "E87-D",
pages = "1247--1253",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "一般社団法人電子情報通信学会",
number = "5",

}

TY - JOUR

T1 - Nonuniform slant correction for handwritten word recognition

AU - Taira, Eiji

AU - Uchida, Seiichi

AU - Sakoe, Hiroaki

PY - 2004/1/1

Y1 - 2004/1/1

N2 - Slant correction is a preprocessing technique to improve segmentation and recognition accuracy for handwritten word recognition. All conventional slant correction techniques were performed by the estimation of the average slant angle and the shear transformation. In this paper, a nonuniform slant correction technique for handwritten word recognition is proposed where the slant correction problem is formulated as a global optimal estimation problem of the sequence of local slant angles. The optimal estimation is performed by a dynamic programming based algorithm. From experimental results it was shown that the present technique outperforms conventional uniform slant correction techniques.

AB - Slant correction is a preprocessing technique to improve segmentation and recognition accuracy for handwritten word recognition. All conventional slant correction techniques were performed by the estimation of the average slant angle and the shear transformation. In this paper, a nonuniform slant correction technique for handwritten word recognition is proposed where the slant correction problem is formulated as a global optimal estimation problem of the sequence of local slant angles. The optimal estimation is performed by a dynamic programming based algorithm. From experimental results it was shown that the present technique outperforms conventional uniform slant correction techniques.

UR - http://www.scopus.com/inward/record.url?scp=2642571862&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2642571862&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:2642571862

VL - E87-D

SP - 1247

EP - 1253

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 5

ER -