A Discriminative Model for On-line Handwritten Japanese Text Retrieval

被引：1
|
作者：
Cheng, Cheng [1 ]
Zhu, Bilan [1 ]
Nakagawa, Masaki [1 ]
机构：
[1] Tokyo Univ Agr & Technol, Dept Comp & Informat Sci, Koganei, Tokyo 1848588, Japan
来源：
11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011) | 2011年
关键词：
text retrieval; discriminative model; geometric context; character recognition;
D O I：
10.1109/ICDAR.2011.306
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper describes an unconstrained on-line handwritten Japanese text retrieval system from character recognition candidates. The system is based on a discriminative model which integrates the scores of character recognition, segmentation and geometric context in search and retrieval, and the parameters are trained by supervised learning. Experiments on TUAT Kuchibue database show that the proposed method can effectively improve the system performance. When the search method with the optimal threshold retrieves for a keyword consisting of two, three or four characters, its f-measure is 0.720, 0.868 or 0.923, respectively.
引用
收藏
页码：1285 / 1288
页数：4
相关论文
共 50 条
  • [21] Distinguishing text from graphics in on-line handwritten ink
    Bishop, CM
    Svensén, M
    Hinton, GE
    NINTH INTERNATIONAL WORKSHOP ON FRONTIERS IN HANDWRITING RECOGNITION, PROCEEDINGS, 2004, : 142 - 147
  • [22] Writing speed normalization for on-line handwritten text recognition
    Pastor, M
    Toselli, A
    Vidal, E
    EIGHTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS 1 AND 2, PROCEEDINGS, 2005, : 1131 - 1135
  • [23] Word extraction from on-line handwritten text lines
    Liwicki, Marcus
    Scherz, Mathias
    Bunke, Horst
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2006, : 929 - +
  • [24] A MRF Model with Parameter Optimization by CRF for On-line Recognition of Handwritten Japanese Characters
    Zhu, Bilan
    Nakagawa, Masaki
    DOCUMENT RECOGNITION AND RETRIEVAL XVIII, 2011, 7874
  • [25] Objective Function Design for MCE-based Combination of On-line and Off-line Character Recognizers for On-line Handwritten Japanese Text Recognition
    Zhu, Bilan
    Gao, JinFeng
    Nakagawa, Masaki
    11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 594 - 598
  • [26] Collection and analysis of on-line handwritten Japanese character patterns
    Matsumoto, K
    Fukushima, T
    Nakagawa, M
    SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 496 - 500
  • [27] Large Improvement in Line-direction-free and Character-orientation-free On-line Handwritten Japanese Text Recognition
    Hao, Yuechan
    Zhu, Bilan
    Nakagawa, Masaki
    2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2014, : 329 - 334
  • [28] On-line writing-box-free recognition of handwritten Japanese text considering character size variations
    Fukushima, T
    Nakagawa, M
    15TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, PROCEEDINGS: PATTERN RECOGNITION AND NEURAL NETWORKS, 2000, : 359 - 363
  • [29] An input panel and recognition engine for on-line handwritten text recognition
    Ramos-Garijo, Rafael
    Martin, Sergio
    Marzal, Andres
    Prat, Federico
    Vilar, Juan Miguel
    Llorens, David
    ARTIFICIAL INTELLIGENCE RESEARCH AND DEVELOPMENT, 2007, 163 : 223 - +
  • [30] On-line Handwritten Japanese Characters Recognition Using A MRF Model with Parameter Optimization by CRF
    Zhu, Bilan
    Nakagawa, Masaki
    11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 603 - 607
12345