RECOGNITION OF HANDWRITTEN DIGITS USING TEMPLATE AND MODEL-MATCHING

被引：35
|
作者：
GADER, P
FORESTER, B
GANZBERGER, M
GILLIES, A
MITCHELL, B
WHALEN, M
YOCUM, T
机构：
[1] Environmental Research Institute of Michigan, Ann Arbor, MI 48107-8618
来源：
PATTERN RECOGNITION | 1991年 / 24卷 / 05期
关键词：
HANDWRITTEN NUMERAL RECOGNITION; TEMPLATE MATCHING; MODEL-BASED CLASSIFICATION; K-NEAREST NEIGHBOR; CASCADED SYSTEMS;
D O I：
10.1016/0031-3203(91)90055-A
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A pipeline strategy for handwritten numeral recognition that combines a two-stage template-based technique and a model-based technique is described. The template matcher combines multiple information sources. The second stage of the template matcher was trained on rejects from the first stage. The template matcher classifies 70-80% of the digits with reliability rates over 99%. It also generates class membership hypotheses for the remaining digits which constrain the model-based system. Recognition rates of 94.03-96.39% and error rates of 0.54%-1.05% are obtained on test data consisting of over 13,000 well-segmented digits from ZIP codes in the USPS mail.
引用
收藏
页码：421 / 431
页数：11
相关论文
共 50 条
  • [1] THE EFFICIENCY OF HOLISTIC TEMPLATE MATCHING IN THE RECOGNITION OF UNCONSTRAINED HANDWRITTEN DIGITS
    LARSEN, A
    BUNDESEN, C
    PSYCHOLOGICAL RESEARCH-PSYCHOLOGISCHE FORSCHUNG, 1992, 54 (03): : 187 - 193
  • [2] Handwritten digits recognition using transfer learning
    Azawi, Nidhal
    COMPUTERS & ELECTRICAL ENGINEERING, 2023, 106
  • [3] Recognition of handwritten digits using structural information
    Behnke, S
    Pfister, M
    Rojas, R
    1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 1391 - 1396
  • [4] An Embodied Model for Handwritten Digits Recognition in a Cognitive Robot
    Di Nuovo, Alessandro
    2017 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2017,
  • [5] Recognition of handwritten Urdu digits using Shape Context
    Yusuf, M
    Haider, T
    INMIC 2004: 8th International Multitopic Conference, Proceedings, 2004, : 569 - 572
  • [6] Representation and recognition of handwritten digits using deformable templates
    Jain, AK
    Zongker, D
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (12) : 1386 - 1391
  • [7] Handwritten Digits Recognition Using Multiple Instance Learning
    Yuan Hanning
    Wang Peng
    2013 IEEE INTERNATIONAL CONFERENCE ON GRANULAR COMPUTING (GRC), 2013, : 408 - 411
  • [8] Classification and recognition of handwritten digits by using mathematical morphology
    Vijaya kumar V.
    Srikrishna A.
    Babu B.R.
    Mani M.R.
    Sadhana, 2010, 35 (4) : 419 - 426
  • [9] Reliable Recognition of Handwritten Digits Using Hamming Network
    Archana, S.
    Madhavi, B. K.
    Krishna, I. V. Murali
    2016 IEEE 6TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTING (IACC), 2016, : 476 - 479
  • [10] A study on handwritten digits recognition using independent components
    Kotani, M
    Ozawa, S
    8TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING, VOLS 1-3, PROCEEDING, 2001, : 1620 - 1625
12345