Recognition of handwritten characters using modified fuzzy hyperline segment neural network

被引：0
|
作者：
Patil, PM [1 ]
Dhabe, PS [1 ]
Kulkarni, U [1 ]
Sontakke, TR [1 ]
机构：
[1] SGGS Coll Engn & Technol, Elect & Comp Sci & Engn Dept, Nanded 431602, India
来源：
PROCEEDINGS OF THE 12TH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1 AND 2 | 2003年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper membership function of fuzzy hyperline segment neural network (FHLSNN) proposed by U.V.Kulkarni and T.R.Sontakke is modified to maintain convexity. The modified membership function is found superior than the function defined by them, which gives relatively lower values to the patterns which are failing close to the hyperline segment (HLS) but far from two end points of HLS. The performance of modified fuzzy hyperline segment neural network (MFHLSNN) is tested with the two splits of FISHER IRIS data and is found superior than FHLSNN. The modified neural network is also found superior than the general fuzzy min-max neural network (GFMM), proposed by Bogdan Gabrys and Andrzej Bargiela, and general fuzzy hypersphere neural network (GFHSNN), proposed by U. V. Kulkarni, D.D.Doye and T. R. Sontakke.
引用
收藏
页码：1418 / 1422
页数：5
相关论文
共 50 条
  • [21] Recognition of multifont Farsi/Arabic characters using a fuzzy neural network
    Namazi, M
    Student, M
    Faez, K
    1996 IEEE TENCON - DIGITAL SIGNAL PROCESSING APPLICATIONS PROCEEDINGS, VOLS 1 AND 2, 1996, : 918 - 922
  • [22] The system of handwritten characters recognition on the basis of Legendre moments and neural network
    Vatkin, M
    Selinger, M
    DESDES '1: PROCEEDINGS OF THE INTERNATIONAL WORKSHOP ON DISCRETE-EVENT SYSTEM DESIGN, 2001, : 259 - 263
  • [23] Integrated segmentation and recognition of connected handwritten characters with recurrent neural network
    Lee, SW
    Lee, EJ
    DOCUMENT RECOGNITION III, 1996, 2660 : 251 - 261
  • [24] Distance features for neural network-based recognition of handwritten characters
    Oh I.-S.
    Suen C.Y.
    International Journal on Document Analysis and Recognition, 1998, 1 (2) : 73 - 88
  • [25] RECOGNITION OF ARABIC HANDWRITTEN CHARACTERS USING RESIDUAL NEURAL NETWORKS
    Al-Taani, Ahmad T.
    Ahmad, Sadeem T.
    JORDANIAN JOURNAL OF COMPUTERS AND INFORMATION TECHNOLOGY, 2021, 7 (02): : 192 - 205
  • [26] Offline handwritten Devanagari modified character recognition using convolutional neural network
    Mamta Bisht
    Richa Gupta
    Sādhanā, 2021, 46
  • [27] Offline handwritten Devanagari modified character recognition using convolutional neural network
    Bisht, Mamta
    Gupta, Richa
    SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES, 2021, 46 (01):
  • [28] Classification and clustering of handwritten numeral characters using modular general fuzzy hypersphere neural network
    Patil, Pradeep M.
    Kulkarni, S.N.
    Doye, D.D.
    Kulkarni, Uday V.
    Sontakke, T.R.
    WSEAS Transactions on Information Science and Applications, 2006, 3 (03): : 672 - 676
  • [29] Fuzzy technique based recognition of handwritten characters
    Suresh, RM
    Arumugam, S
    FUZZY LOGIC AND APPLICATIONS, 2006, 2955 : 297 - 308
  • [30] Fuzzy recognition of offline handwritten numeric characters
    Batuwita, K. B. M. R.
    Bandara, G. E. M. D. C.
    2006 IEEE CONFERENCE ON CYBERNETICS AND INTELLIGENT SYSTEMS, VOLS 1 AND 2, 2006, : 766 - +
12345