Ligature modeling for online cursive script recognition

被引:28
|
作者
Sin, BK [1 ]
Kim, JH [1 ]
机构
[1] KOREA ADV INST SCI & TECHNOL,DEPT COMP SCI,YUSONG KU,TAEJON 305701,SOUTH KOREA
关键词
online character recognition; cursive script; Korean character; ligature; hidden Markov model; network searching;
D O I
10.1109/34.601250
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Online recognition of cursive words is a difficult task owing to variable shape and ambiguous letter boundaries. The approach proposed in this paper is based on hidden Markov modeling of letters and inter-letter patterns called ligatures occurring in cursive script. For each of the letters and the ligatures we create one HMM that models temporal and spatial variability of handwriting. By networking the two kinds of HMMs, we can design a network model for all words or composite characters. The network incorporates the knowledge sources of grammatical and structural constraints so that it can better capture the characteristics of handwriting. Given the network, the problem of recognition is formulated into that of finding the most likely path from the start node to the end node. A dynamic programming-based search for the optimal input-network alignment performs character recognition and letter segmentation simultaneously and efficiently. Experiments on Korean character showed correct recognition of up to 93.3 percent on unconstrained samples. It has also been compared with several other schemes of HMM-based recognition to characterize the proposed approach.
引用
收藏
页码:623 / 633
页数:11
相关论文
共 50 条
  • [21] CLUSTER NETWORK FOR RECOGNITION OF HANDWRITTEN, CURSIVE SCRIPT CHARACTERS
    HOFFMAN, J
    SKRZYPEK, J
    VIDAL, JJ
    NEURAL NETWORKS, 1993, 6 (01) : 69 - 78
  • [22] OFF-LINE CURSIVE SCRIPT WORD RECOGNITION
    BOZINOVIC, RM
    SRIHARI, SN
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (01) : 68 - 83
  • [23] Normalized Fourier coefficients for cursive Arabic script recognition
    Aissaoui, A.
    Haouari, A.
    Applied Signal Processing, 1999, 6 (03): : 115 - 122
  • [24] A 'CURSIVE SCRIPT'
    COLE, R
    AGENDA, 1990, 28 (03): : 23 - 23
  • [25] Cursive Script Recognition using Wildcards and Multiple Experts
    A. Hennig
    N. Sherkat
    Pattern Analysis & Applications, 2001, 4 : 51 - 60
  • [26] Semantic analysis for large vocabulary cursive script recognition
    1600, IAPR TC-11 and TC-10; IEEE Computer Society (IEEE, Los Alamitos, CA, USA):
  • [27] MACHINE RECOGNITION OF HUMAN LANGUAGE .3. CURSIVE SCRIPT RECOGNITION
    LINDGREN, N
    IEEE SPECTRUM, 1965, 2 (05) : 104 - &
  • [28] CURSIVE ENGLISH SCRIPT RECOGNITION - A KNOWLEDGE-BASED SYSTEM
    RAO, PVS
    AJITHA, TM
    CURRENT SCIENCE, 1995, 69 (05): : 420 - 425
  • [29] An HMM-MLP Hybrid Model for Cursive Script Recognition
    Jin Ho Kim
    Kye Kyung Kim
    Ching Y. Suen
    Pattern Analysis & Applications, 2000, 3 : 314 - 324
  • [30] Syntactic methodology of pruning large lexicons in cursive script recognition
    Madhvanath, S
    Krpasundar, V
    Govindaraju, V
    PATTERN RECOGNITION, 2001, 34 (01) : 37 - 46