The advantage of using an HMM-based approach for faxed word recognition

被引：30
|
作者：
Elms A.J. [1 ,2 ]
Procter S. [1 ]
Illingworth J. [1 ]
机构：
[1] School of Electronic Engineering, Information Technology and Mathematics, University of Surrey, Guildford
[2] Fujitsu Microelectronics Ltd., Maidenhead, Berkshire
来源：
International Journal on Document Analysis and Recognition | 1998年 / 1卷 / 1期
关键词：
Hidden Markov models; OCR; Word recognition;
D O I：
10.1007/s100320050003
中图分类号：
学科分类号：
摘要：
A method for word recognition based on the use of hidden Markov models (HMMs) is described. An evaluation of its performance is presented using a test set of real printed documents that have been subjected to severe photocopy and fax transmission distortions. A comparison with a commercial OCR package highlights the inherent advantages of a segmentation-free recognition strategy when the word images are severely distorted, as well as the importance of using contextual knowledge. The HMM method makes only one quarter of the number of word errors made by the commercial package when tested on word images taken from faxed pages. © 1998 Springer-Verlag Berlin Heidelberg.
引用
收藏
页码：18 / 36
页数：18
相关论文
共 50 条
  • [41] HMM-based Speech Recognition Using Decision Trees Instead of GMMs
    Teunen, Remco
    Akamine, Masami
    [J]. INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 617 - 620
  • [42] HMM-based human action recognition using multiview image sequences
    Ahmad, Mohiuddin
    Lee, Seong-Whan
    [J]. 18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2006, : 263 - +
  • [43] A study on rescoring using HMM-based detectors for continuous speech recognition
    Fu, Qiang
    Juang, Biing-Hwang
    [J]. 2007 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, VOLS 1 AND 2, 2007, : 570 - 575
  • [44] POSTPROCESSOR USING FUZZY VECTOR QUANTIZER IN HMM-BASED SPEECH RECOGNITION
    KIM, HR
    LEE, HS
    [J]. ELECTRONICS LETTERS, 1991, 27 (22) : 1998 - 2000
  • [45] Speaker state recognition using an HMM-based feature extraction method
    Gajsek, R.
    Mihelic, F.
    Dobrisek, S.
    [J]. COMPUTER SPEECH AND LANGUAGE, 2013, 27 (01): : 135 - 150
  • [46] A Study on a HMM-Based State Machine Approach for Lane Changing Behavior Recognition
    David, Ruth
    Soeffker, Dirk
    [J]. IEEE ACCESS, 2022, 10 : 122954 - 122964
  • [47] HMM-based handwritten word recognition:: on the optimization of the number of states, training iterations and Gaussian components
    Günter, S
    Bunke, H
    [J]. PATTERN RECOGNITION, 2004, 37 (10) : 2069 - 2079
  • [48] An improved maximum model distance approach for HMM-based speech recognition systems
    He, QH
    Kwong, S
    Man, KF
    Tang, KS
    [J]. PATTERN RECOGNITION, 2000, 33 (10) : 1749 - 1758
  • [49] Combining HMM-based two-pass classifiers for off-line word recognition
    Wang, WW
    Brakensiek, A
    Rigoll, G
    [J]. 16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL III, PROCEEDINGS, 2002, : 151 - 154
  • [50] Line handwritten Devanagari word recognition: An HMM based approach
    Parui, Swapan Kumar
    Shaw, Bikash
    [J]. PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PROCEEDINGS, 2007, 4815 : 528 - 535
12345