Research of Numeral Character Recognition Technology Based on Wavelet Analysis and RBF Neural Networks

被引：0
|
作者：
Song, Qingkun [1 ]
Zhou, Teng [1 ]
机构：
[1] Harbin Univ Sci & Technol, Automat Coll, Harbin, Peoples R China
来源：
2011 INTERNATIONAL CONFERENCE ON ELECTRONICS, COMMUNICATIONS AND CONTROL (ICECC) | 2011年
关键词：
character recognition; wavelet analysis; energy eigenvector; RBF neural networks;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Taking advantage of the ability of revealing the images details and the local characteristics in the time-frequency domain, this paper presents a new method of character images recognition, which is based on wavelet packets analysis and RBF neural networks. Firstly this paper decomposes character images with wavelet analysis, then reconstructs the discrete wavelet coefficients and calculates energy values, then extracts energy values from various character images to construct energy eigenvectors as the input of the RBF neural networks. By choosing the number of hide nodes and the learning algorithm of weight, a perfect RBF neural network can be created. At last the RBF neural network carries on identifying the numeral character images. The experiment results show that a high rate of recognition can be obtained by this method.
引用
收藏
页码：1603 / 1606
页数：4
相关论文
共 50 条
  • [11] Enhancing the Odia Handwritten Character and Numeral Recognition System's Performance with an Ensemble of Deep Neural Networks
    Das, Mamatarani
    Panda, Mrutyunjaya
    Sahoo, Soumya
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (02) : 684 - 697
  • [12] Deep Neural Network with RBF and Sparse auto-encoders for Numeral Recognition
    Mellouli, Dorra
    Hamdani, Tarek M.
    Aimi, Adel M.
    2015 15TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS (ISDA), 2015, : 468 - 472
  • [13] RBF neural networks for hand-based biometiric recognition
    Sanchez-Reillo, R
    Sanchez-Avila, C
    AUDIO- AND VIDEO-BASED BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS, 2001, 2091 : 330 - 335
  • [14] The application of convolution neural networks in handwritten numeral recognition
    College of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao, China
    Int. J. Database Theory Appl., 3 (367-376):
  • [15] Research of brige deflection restoring based on correlation analysis and RBF neural networks
    Hu Shunren
    Chen Weimin
    Fu Yumei
    Proceedings of the International Conference on Mechanical Transmissions, Vols 1 and 2, 2006, : 1670 - 1673
  • [16] Character recognition based on hierarchical REF neural networks
    Li Yuelong
    Li Jinping
    Li, Meng
    ISDA 2006: SIXTH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS, VOL 1, 2006, : 127 - 132
  • [17] Handwritten character recognition based on hybrid neural networks
    Wang, P
    Sun, GM
    Zhang, XM
    NEURAL NETWORK AND DISTRIBUTED PROCESSING, 2001, 4555 : 65 - 70
  • [18] Contour-based handwritten numeral recognition using multiwavelets and neural networks
    Chen, GY
    Bui, TD
    Krzyzak, A
    PATTERN RECOGNITION, 2003, 36 (07) : 1597 - 1604
  • [19] The research with Gabor wavelet neural networks algorithm on target recognition
    Sun, HG
    Pan, YX
    Zhang, JB
    Electronic Imaging and Multimedia Technology IV, 2005, 5637 : 339 - 346
  • [20] Research and prediction of atmospheric pollution based on wavelet and RBF neural network
    Anhui University of Technology and Science, Wuhu 241000, China
    不详
    Xitong Fangzhen Xuebao, 2006, 5 (1411-1413):
12345