LEREC - A NN/HMM HYBRID FOR ONLINE HANDWRITING RECOGNITION

被引：64
|
作者：
BENGIO, Y [1 ]
LECUN, Y [1 ]
NOHL, C [1 ]
BURGES, C [1 ]
机构：
[1] UNIV MONTREAL,DEPT IRO,MONTREAL,PQ H3C 3J7,CANADA
来源：
NEURAL COMPUTATION | 1995年 / 7卷 / 06期
关键词：
D O I：
10.1162/neco.1995.7.6.1289
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We introduce a new approach for on-line recognition of handwritten words written in unconstrained mixed style. The preprocessor performs a word-level normalization by fitting a model of the word structure using the EM algorithm. Words are then coded into low resolution ''annotated images'' where each pixel contains information about trajectory direction and curvature. The recognizer is a convolution network that can be spatially replicated. From the network output, a hidden Markov model produces word scores. The entire system is globally trained to minimize word-level errors.
引用
收藏
页码：1289 / 1303
页数：15
相关论文
共 50 条
  • [11] Hybrid HMM-NN architectures for connected digit recognition
    Cosi, P
    IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL V, 2000, : 85 - 90
  • [12] Multi-layer fuzzy HMM for online handwriting shape recognition
    Li, CY
    Ji, HB
    Pei, JH
    2004 7TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS 1-3, 2004, : 1427 - 1430
  • [13] Data-driven design of HMM topology for online handwriting recognition
    Lee, JJ
    Kim, J
    Kim, JH
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2001, 15 (01) : 107 - 121
  • [14] HMM-based online handwriting recognition system for Telugu symbols
    Babu, V. Jagadeesh
    Prasanth, L.
    Sharma, R. Raghunath
    Rao, G. V. Prabhakara
    Bharath, A.
    ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2007, : 63 - +
  • [15] Comparing NN paradigms in hybrid NN/HMM speech recognition using tied posteriors
    Stadermann, J
    Rigoll, G
    ASRU'03: 2003 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING ASRU '03, 2003, : 89 - 93
  • [16] Hybrid NN/HMM acoustic modeling techniques for distributed speech recognition
    Stadermann, Jan
    Rigoll, Gerhard
    SPEECH COMMUNICATION, 2006, 48 (08) : 1037 - 1046
  • [17] A MSD-HMM approach to pen trajectory modeling for online handwriting recognition
    Ma, Lei
    Wu, Yi-Jian
    Liu, Peng
    Soong, Frank
    ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2007, : 128 - 132
  • [18] Hybrid HMM-NN for speech recognition and prior class probabilities
    Albesano, D
    Gemello, R
    Mana, F
    ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 2391 - 2395
  • [19] A Bayesian bi-gram scheme for HMM online handwriting recognition algorithm
    Hasegawa, T
    Akamatsu, K
    Matsumoto, T
    SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 1012 - 1016
  • [20] Hmm topology optimization for handwriting recognition
    Li, DF
    Biem, A
    Subrahmonia, 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, 2001, : 1521 - 1524
12345