An efficient post-processing approach for off-line handwritten Chinese address recognition

被引：0
|
作者：
Long, Chong [1 ]
Zhu, Xiaoyan [1 ]
Huang, Kaizhu [2 ]
Sun, Jun [2 ]
Hotta, Yoshinobu [3 ]
Naoi, Satoshi [3 ]
机构：
[1] Tsinghua Univ, Dept Comp Sci & Technol, State Key Lab Intelligent Technol & Syst, Beijing 100084, Peoples R China
[2] Fujitsu R&D Ctr Co Ltd, Informat Technol Lab, Beijing 100016, Peoples R China
[3] Fujitsu Labs Ltd, Kawasaki, Kanagawa 2118588, Japan
来源：
2006 8TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, VOLS 1-4 | 2006年
关键词：
OCR; post-processing; language mode; ME model;
D O I：
暂无
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
Language model is widely used in OCR post-processing. In this paper, based on language model, we propose a two-step method for post-processing of off-line handwritten Chinese address recognition. According to the characteristics of high level and low level addresses, two different strategies are used: for high level addresses, word-based language model is used with weighed matching search algorithm proposed; for low level addresses, ME model is implemented with similar character method. After post-processing, recognition accuracy rises from 41.60% to 78.19%. which means 62.65% errors reduction.
引用
收藏
页码：1063 / +
页数：2
相关论文
共 50 条
  • [41] Combining discrete orthogonal moments and dhmms for off-line handwritten Chinese character recognition
    Wang, Xianmei
    Yang, Yang
    Huang, Kang
    PROCEEDINGS OF THE FIFTH IEEE INTERNATIONAL CONFERENCE ON COGNITIVE INFORMATICS, VOLS 1 AND 2, 2006, : 788 - 793
  • [42] Research of Off-line Handwritten Chinese Character Recognition System Based on Feedback Structure
    Wang, Jianping
    Cao, Huiying
    Wang, Jinling
    Zhu, Chenghui
    MATERIALS SCIENCE AND INFORMATION TECHNOLOGY, PTS 1-8, 2012, 433-440 : 7046 - +
  • [43] A hybrid Handwritten Chinese Address Recognition approach
    Huang, Kaizhu
    Sun, Jun
    Hotta, Yoshinobu
    Fujimoto, Katsuhito
    Naoi, Satoshi
    Long, Chong
    Zhuang, Li
    Zhu, Xiaoyan
    NEURAL INFORMATION PROCESSING, PT 2, PROCEEDINGS, 2006, 4233 : 88 - 98
  • [44] Lexical post-processing optimization for handwritten word recognition
    Carbonnel, S
    Anquetil, E
    SEVENTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2003, : 477 - 481
  • [45] Contextual post-processing based on the confusion matrix in offline handwritten Chinese script recognition
    Li, YX
    Tan, CL
    Ding, XQ
    Liu, CS
    PATTERN RECOGNITION, 2004, 37 (09) : 1901 - 1912
  • [46] Using neural network classifier in post-processing system for handwritten Chinese character recognition
    Xu, RF
    Yeung, DS
    Wang, XZ
    2001 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5: E-SYSTEMS AND E-MAN FOR CYBERNETICS IN CYBERSPACE, 2002, : 1497 - 1502
  • [47] Recognition of off-line handwritten arabic words using Hidden Markov Model approach
    Alma'adeed, S
    Higgens, C
    Elliman, D
    16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL III, PROCEEDINGS, 2002, : 481 - 484
  • [48] A Topological Structure Construction Approach and its Application in Off-line Handwritten Digit Recognition
    Duan, Huichuan
    Yang, Jinwei
    Liu, Xiyu
    Liu, Hong
    2008 3RD INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING AND APPLICATIONS, VOLS 1 AND 2, 2008, : 356 - +
  • [49] New scheme for off-line handwritten connected digit recognition
    Middle East Technical Univ, Ankara, Turkey
    Int Conf Knowledge Based Intell Electron Syst Proc KES, (329-335):
  • [50] HMM-based approach for off-line unconstrained handwritten word modeling and recognition
    Concordia Univ, Montreal, Canada
    IEEE Trans Pattern Anal Mach Intell, 8 (752-760):
12345