Hidden Markov models combining discrete symbols and continuous attributes in handwriting recognition

被引：25
|
作者：
Xue, HH
Govindaraju, V
机构：
[1] IBM Corp, Adv Clustering Technol Team, Poughkeepsie, NY 12601 USA
[2] Ctr Document Anal & Recognit, Amherst, NY 14228 USA
来源：
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 2006年 / 28卷 / 03期
关键词：
Markov processes; handwriting analysis;
D O I：
10.1109/TPAMI.2006.55
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Prior arts in handwritten word recognition model either discrete features or continuous features, but not both. This paper combines discrete symbols and continuous attributes into structural handwriting features and model, them by transition-emitting and state-emitting hidden Markov models. The models are rigorously defined and experiments have proven their effectiveness.
引用
收藏
页码：458 / 462
页数：5
相关论文
共 50 条
  • [1] A Stochastic model combining discrete symbols and continuous attributes and its application to handwriting recognition
    Xue, HH
    Govindaraju, V
    [J]. DOCUMENT ANALYSIS SYSTEM V, PROCEEDINGS, 2002, 2423 : 70 - 81
  • [2] A Hidden Markov Models combination framework for handwriting recognition
    T. Artières
    N. Gauthier
    P. Gallinari
    B. Dorizzi
    [J]. Document Analysis and Recognition, 2003, 5 (4): : 233 - 243
  • [3] Chinese handwriting recognition using hidden Markov models
    Bing, F
    Ding, XQ
    Wu, YS
    [J]. 16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL III, PROCEEDINGS, 2002, : 212 - 215
  • [4] Speech recognition on an FPA using discrete and continuous hidden Markov models
    Melnikoff, SJ
    Quigley, SF
    Russell, MJ
    [J]. FIELD-PROGRAMMABLE LOGIC AND APPLICATIONS, PROCEEDINGS: RECONFIGURABLE COMPUTING IS GOING MAINSTREAM, 2002, 2438 : 202 - 211
  • [5] Improved Handwriting Recognition by Combining Two Forms of Hidden Markov Models and a Recurrent Neural Network
    Frinken, Volkmar
    Peter, Tim
    Fischer, Andreas
    Bunke, Horst
    Do, Trinh-Minh-Tri
    Artieres, Thierry
    [J]. COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PROCEEDINGS, 2009, 5702 : 189 - +
  • [6] Hidden Markov Models for couples of letters applied to handwriting recognition
    Dupré, X
    Augustin, E
    [J]. PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, 2004, : 618 - 621
  • [7] Graphical Models for Discrete Hidden Markov Models in Speech Recognition
    Miguel, Antonio
    Ortega, Alfonso
    Buera, Luis
    Lleida, Eduardo
    [J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 1387 - 1390
  • [8] Features Modelling in Discrete and Continuous Hidden Markov Models for Handwritten Arabic Words Recognition
    Benzenache, Amine
    Seridi, Hamid
    Akdag, Herman
    [J]. INTERNATIONAL ARAB JOURNAL OF INFORMATION TECHNOLOGY, 2017, 14 (05) : 681 - 690
  • [9] Initialization of hidden Markov models for unconstrained on-line handwriting recognition
    Nathan, K
    Senior, A
    Subrahmonia, J
    [J]. 1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 3502 - 3505
  • [10] Minimum Classification Error training of Hidden Markov Models for handwriting recognition
    Biem, AE
    [J]. 2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING - VOL IV: SIGNAL PROCESSING FOR COMMUNICATIONS; VOL V: SIGNAL PROCESSING EDUCATION SENSOR ARRAY & MULTICHANNEL SIGNAL PROCESSING AUDIO & ELECTROACOUSTICS; VOL VI: SIGNAL PROCESSING THEORY & METHODS STUDENT FORUM, 2001, : 1529 - 1532
12345