ANALYSIS OF PERSONAL INFORMATION IN HANDWRITTEN CHARACTERS, AND AUTOMATIC WRITER RECOGNITION USING A SPECTRAL RESOLUTION TECHNIQUE.

Takeshi Shakunaga, Hiroshi Kaneko, Eiji Yodogawa

Research output: Contribution to journalArticle

Abstract

This paper proposes application of a new spectral resolution technique of 2nd order statistics for the purpose of extracting personal information from handwritten characters. This resolution technique was formulated based on a textural analysis viewpoint, and put to use for automatic writer recognition. Three algorithms were developed for text-independent identification, text-dependent identification and text-dependent verification. Experiments with five characters regarding text-dependent writer identification show that the identification rate is 99. 979% for 30 persons. Moreover, in verification experiments, false acceptance was only 0. 0034% when false rejection was 5. 2% for 29 registrants and five characters.

Original languageEnglish
Pages (from-to)35-46
Number of pages12
JournalDenki Tsushin Kenkyujo kenkyu jitsuyoka hokoku
Volume34
Issue number1
Publication statusPublished - 1985
Externally publishedYes

Fingerprint

Spectral resolution
Experiments
Statistics

ASJC Scopus subject areas

  • Engineering(all)

Cite this

@article{eaaa81e05a0c42f886e48eba2cc2904c,
title = "ANALYSIS OF PERSONAL INFORMATION IN HANDWRITTEN CHARACTERS, AND AUTOMATIC WRITER RECOGNITION USING A SPECTRAL RESOLUTION TECHNIQUE.",
abstract = "This paper proposes application of a new spectral resolution technique of 2nd order statistics for the purpose of extracting personal information from handwritten characters. This resolution technique was formulated based on a textural analysis viewpoint, and put to use for automatic writer recognition. Three algorithms were developed for text-independent identification, text-dependent identification and text-dependent verification. Experiments with five characters regarding text-dependent writer identification show that the identification rate is 99. 979{\%} for 30 persons. Moreover, in verification experiments, false acceptance was only 0. 0034{\%} when false rejection was 5. 2{\%} for 29 registrants and five characters.",
author = "Takeshi Shakunaga and Hiroshi Kaneko and Eiji Yodogawa",
year = "1985",
language = "English",
volume = "34",
pages = "35--46",
journal = "Denki Tsushin Kenkyujo kenkyu jitsuyoka hokoku",
issn = "0415-3200",
number = "1",

}

TY - JOUR

T1 - ANALYSIS OF PERSONAL INFORMATION IN HANDWRITTEN CHARACTERS, AND AUTOMATIC WRITER RECOGNITION USING A SPECTRAL RESOLUTION TECHNIQUE.

AU - Shakunaga, Takeshi

AU - Kaneko, Hiroshi

AU - Yodogawa, Eiji

PY - 1985

Y1 - 1985

N2 - This paper proposes application of a new spectral resolution technique of 2nd order statistics for the purpose of extracting personal information from handwritten characters. This resolution technique was formulated based on a textural analysis viewpoint, and put to use for automatic writer recognition. Three algorithms were developed for text-independent identification, text-dependent identification and text-dependent verification. Experiments with five characters regarding text-dependent writer identification show that the identification rate is 99. 979% for 30 persons. Moreover, in verification experiments, false acceptance was only 0. 0034% when false rejection was 5. 2% for 29 registrants and five characters.

AB - This paper proposes application of a new spectral resolution technique of 2nd order statistics for the purpose of extracting personal information from handwritten characters. This resolution technique was formulated based on a textural analysis viewpoint, and put to use for automatic writer recognition. Three algorithms were developed for text-independent identification, text-dependent identification and text-dependent verification. Experiments with five characters regarding text-dependent writer identification show that the identification rate is 99. 979% for 30 persons. Moreover, in verification experiments, false acceptance was only 0. 0034% when false rejection was 5. 2% for 29 registrants and five characters.

UR - http://www.scopus.com/inward/record.url?scp=0021903612&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0021903612&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0021903612

VL - 34

SP - 35

EP - 46

JO - Denki Tsushin Kenkyujo kenkyu jitsuyoka hokoku

JF - Denki Tsushin Kenkyujo kenkyu jitsuyoka hokoku

SN - 0415-3200

IS - 1

ER -