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

被引：121
|
作者：
Kato, N [1 ]
Suzuki, M
Omachi, S
Aso, H
Nemoto, Y
机构：
[1] Tohoku Univ, Grad Sch Informat Sci, Sendai, Miyagi 9808579, Japan
[2] Tokyo Natl Coll Technol, Dept Comp Sci, Hachioji, Tokyo 1938610, Japan
[3] Tohoku Univ, Grad Sch Engn, Sendai, Miyagi 9808579, Japan
来源：
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1999年 / 21卷 / 03期
关键词：
handwritten Chinese and Japanese character; recognition; directional element feature; city block distance with deviation; asymmetric Mahalanobis distance; ETL9B;
D O I：
10.1109/34.754617
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper presents a precise system for handwritten Chinese and Japanese character recognition. Before extracting directional element feature (DEF) 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%.
引用
收藏
页码：258 / 262
页数：5
相关论文
共 50 条
  • [1] Handwritten character recognition system using modified Mahalanobis distance
    Kato, Nei
    Abe, Masato
    Nemoto, Yoshiaki
    Systems and Computers in Japan, 1997, 28 (01): : 46 - 55
  • [2] A Handwritten Chinese Character Recognition by Adaptive Mahalanobis Distance
    Oohori, T.
    Yamamoto, T.
    Hori, M.
    Watanabe, K.
    Denki Gakkai Ronbunshi. C, Erekutoronikusu Joho Kogaku, Shisutemu, 1997, 117 (05):
  • [3] Handwritten Character Recognition System using a Simple Feature
    Moni, Bindu S.
    Raju, G.
    PROCEEDINGS OF THE 2012 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI'12), 2012, : 728 - 734
  • [4] Analysis and improvement of directional element feature for off-line handwritten Chinese character recognition
    Chen, YB
    Wu, YS
    Beveridge, JR
    DOCUMENT RECOGNITION V, 1998, 3305 : 72 - 80
  • [5] A feature for character recognition based on directional distance distributions
    Oh, IS
    Suen, CY
    PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS 1 AND 2, 1997, : 288 - 292
  • [6] High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps
    Zhong, Zhuoyao
    Jin, Lianwen
    Xie, Zecheng
    2015 13TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2015, : 846 - 850
  • [7] Handwritten character recognition using the continuos distance transformation
    Arlandis, J
    Perez-Cortes, JC
    Llobet, R
    15TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, PROCEEDINGS: COMPUTER VISION AND IMAGE ANALYSIS, 2000, : 940 - 943
  • [8] Feature Extraction Using Geometrical Features for Malayalam Handwritten Character Recognition System
    Thushara, K.
    James, Ajay
    Saravanan, C.
    2017 2ND IEEE INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, SIGNAL PROCESSING AND NETWORKING (WISPNET), 2017, : 477 - 482
  • [9] Bangla Handwritten Numeral Character Recognition Using Directional Pattern
    Ibn Aziz, Talha
    Rubel, Al Shahriar
    Salekin, Md Sirajus
    Kushol, Rafsanjany
    2017 20TH INTERNATIONAL CONFERENCE OF COMPUTER AND INFORMATION TECHNOLOGY (ICCIT), 2017,
  • [10] Handwritten character recognition using combined gradient and wavelet feature
    Zhang, Weipeng
    Tang, Yuan Yan
    Xue, Yun
    2006 INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY, PTS 1 AND 2, PROCEEDINGS, 2006, : 662 - 667
12345