A handwritten character recognition system using directional element feature and asymmetric mahalanobis distance

Nei Kato; M. Suzuki; S. Omachi; H. Aso; Y. Nemoto

doi:10.1109/34.754617

A handwritten character recognition system using directional element feature and asymmetric mahalanobis distance

Nei Kato, M. Suzuki, S. Omachi, H. Aso, Y. Nemoto

Research output: Contribution to journal › Article › peer-review

188 Citations (Scopus)

Abstract

This paper presents a precise system for handwritten Chinese and Japanese character recognition. Before extracting directional element feature (DBF) from each character image transformation based on partial inclination detection (TPID) is used to reduce undesired effects of degraded images. In the recognition process city block distance with deviation (CBDD) and asymmetric Mahalanobis distance (AMD) are proposed for rough classification and fine classification. With this recognition system the experimental result of the database ETL9B reaches to 99.42%. Index Terms-Handwritten Chinese and Japanese character recognition directional element feature city block distance with deviation asymmetric Mahalanobis distance ETL9B.

Original language	English
Pages (from-to)	258-262
Number of pages	5
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	21
Issue number	3
DOIs	https://doi.org/10.1109/34.754617
Publication status	Published - 1999

Access to Document

10.1109/34.754617

Cite this

@article{a1de5ca690854742bbcb8d16df2bad6e,

title = "A handwritten character recognition system using directional element feature and asymmetric mahalanobis distance",

abstract = "This paper presents a precise system for handwritten Chinese and Japanese character recognition. Before extracting directional element feature (DBF) from each character image transformation based on partial inclination detection (TPID) is used to reduce undesired effects of degraded images. In the recognition process city block distance with deviation (CBDD) and asymmetric Mahalanobis distance (AMD) are proposed for rough classification and fine classification. With this recognition system the experimental result of the database ETL9B reaches to 99.42%. Index Terms-Handwritten Chinese and Japanese character recognition directional element feature city block distance with deviation asymmetric Mahalanobis distance ETL9B.",

author = "Nei Kato and M. Suzuki and S. Omachi and H. Aso and Y. Nemoto",

note = "Funding Information: The authors wish to thank Dr. Fang Sun at Tohoku University for fruitful advice. They would like to thank Mr. Elias Ross for helpful comments. This work was supported in part by the Ministry of Education, Science, Sports and Culture, Grant-in-Aid for Scientific Research (B), 08680421, 1996.",

year = "1999",

doi = "10.1109/34.754617",

language = "English",

volume = "21",

pages = "258--262",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "3",

}

TY - JOUR

T1 - A handwritten character recognition system using directional element feature and asymmetric mahalanobis distance

AU - Kato, Nei

AU - Suzuki, M.

AU - Omachi, S.

AU - Aso, H.

AU - Nemoto, Y.

N1 - Funding Information: The authors wish to thank Dr. Fang Sun at Tohoku University for fruitful advice. They would like to thank Mr. Elias Ross for helpful comments. This work was supported in part by the Ministry of Education, Science, Sports and Culture, Grant-in-Aid for Scientific Research (B), 08680421, 1996.

PY - 1999

Y1 - 1999

N2 - This paper presents a precise system for handwritten Chinese and Japanese character recognition. Before extracting directional element feature (DBF) from each character image transformation based on partial inclination detection (TPID) is used to reduce undesired effects of degraded images. In the recognition process city block distance with deviation (CBDD) and asymmetric Mahalanobis distance (AMD) are proposed for rough classification and fine classification. With this recognition system the experimental result of the database ETL9B reaches to 99.42%. Index Terms-Handwritten Chinese and Japanese character recognition directional element feature city block distance with deviation asymmetric Mahalanobis distance ETL9B.

AB - This paper presents a precise system for handwritten Chinese and Japanese character recognition. Before extracting directional element feature (DBF) from each character image transformation based on partial inclination detection (TPID) is used to reduce undesired effects of degraded images. In the recognition process city block distance with deviation (CBDD) and asymmetric Mahalanobis distance (AMD) are proposed for rough classification and fine classification. With this recognition system the experimental result of the database ETL9B reaches to 99.42%. Index Terms-Handwritten Chinese and Japanese character recognition directional element feature city block distance with deviation asymmetric Mahalanobis distance ETL9B.

UR - http://www.scopus.com/inward/record.url?scp=0033099691&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033099691&partnerID=8YFLogxK

U2 - 10.1109/34.754617

DO - 10.1109/34.754617

M3 - Article

AN - SCOPUS:0033099691

SN - 0162-8828

VL - 21

SP - 258

EP - 262

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 3

ER -

A handwritten character recognition system using directional element feature and asymmetric mahalanobis distance

Abstract

Access to Document

Other files and links

Fingerprint

Cite this