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
  • [21] Handwritten digits recognition using Hough transform and neural networks
    Castellano, G
    Sandler, MB
    ISCAS 96: 1996 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS - CIRCUITS AND SYSTEMS CONNECTING THE WORLD, VOL 3, 1996, : 313 - 316
  • [22] Recognition of degraded handwritten digits using dynamic Bayesian networks
    Likforman-Sulem, Laurence
    Sigelle, Marc
    DOCUMENT RECOGNITION AND RETRIEVAL XIV, 2007, 6500
  • [23] Recognition of Handwritten English and Digits Using Stroke Features and MLP
    Chen, Chung-Hsing
    Huang, Zih-Hao
    Huang, Ko-Wei
    2022 JOINT 12TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING AND INTELLIGENT SYSTEMS AND 23RD INTERNATIONAL SYMPOSIUM ON ADVANCED INTELLIGENT SYSTEMS (SCIS&ISIS), 2022,
  • [24] Handwritten recognition of Hiragana and Katakana characters based on template matching algorithm
    Septiana, Y.
    Mulyani, A.
    Kurniadi, D.
    Hasanudin, H.
    5TH ANNUAL APPLIED SCIENCE AND ENGINEERING CONFERENCE (AASEC 2020), 2021, 1098
  • [25] Enhanced Handwritten Character Recognition Algorithm Based on Template Matching Method
    Hui, Wang
    Jie, Liu
    ELECTRONIC INFORMATION AND ELECTRICAL ENGINEERING, 2012, 19 : 574 - 578
  • [26] ON ASYMPTOTIC MODEL-MATCHING
    MILLER, DE
    DAVISON, EJ
    MATHEMATICS OF CONTROL SIGNALS AND SYSTEMS, 1993, 6 (04) : 322 - 340
  • [27] An improved hybrid learning model based handwritten digits recognition approach
    Xu Q.-Z.
    Yang L.-X.
    Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, 2010, 32 (02): : 433 - 438
  • [28] Ncfm: Accurate Handwritten Digits Recognition using Convolutional Neural Networks
    Yin, Yan
    Wu, JunMin
    Zheng, HuanXin
    2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2016, : 525 - 531
  • [29] Cloud Services using Hardware Accelerators: The case of Handwritten Digits Recognition
    Bougioukou, Eleni
    Toulgaridis, Nikos
    Antonakopoulos, Theodore
    2017 6TH INTERNATIONAL CONFERENCE ON MODERN CIRCUITS AND SYSTEMS TECHNOLOGIES (MOCAST), 2017,
  • [30] Handwritten digits parameterisation for HMM based recognition
    Travieso, CM
    Morales, CR
    Alonso, IG
    Ferrer, MA
    SEVENTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING AND ITS APPLICATIONS, 1999, (465): : 770 - 774
12345