Extended Fuzzy Hyperline Segment Neural Network for Handwritten Character Recognition

被引：0
|
作者：
Pawar, Dipti [1 ]
机构：
[1] Sinhgad Coll Engn, Dept Comp Sci, Pune, Maharashtra, India
来源：
INTERNATIONAL MULTICONFERENCE OF ENGINEERS AND COMPUTER SCIENTISTS, IMECS 2012, VOL I | 2012年
关键词：
Fuzzy Neural Network; Feature Extraction; Hyperline Segment; Handwritten Character Recognition;
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：
This paper deals with simple and effective set of features for character representation. These features are computed within regularly placed windows spanning the character bitmap; consist of a combination of average pixel density and measures of local alignment along some directions. NIST database and Devnagari digit databases are used for experimentation. In NIST database, training set consists of 60,000 patterns and testing set consist of 10,000 patterns. Devnagari digit database consist of 500 patterns. It is divided in two parts. Training set consists of 300 patterns and testing set consists of 200 patterns. These features used in conjunction with Extended Fuzzy Hyperline Segment Neural network (EFHLSNN). The performance of EFHLSNN is found to be superior compared to FHLSNN with respect to training time, recall time per pattern and recognition rate.
引用
收藏
页码：43 / 46
页数：4
相关论文
共 50 条
  • [1] Fuzzy hyperline segment neural network for rotation invariant handwritten character recognition
    Kulkarni, UV
    Sontakke, TR
    Randale, GD
    [J]. IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2001, : 2918 - 2923
  • [2] Recognition of handwritten characters using modified fuzzy hyperline segment neural network
    Patil, PM
    Dhabe, PS
    Kulkarni, U
    Sontakke, TR
    [J]. PROCEEDINGS OF THE 12TH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1 AND 2, 2003, : 1418 - 1422
  • [3] Fuzzy hyperline segment clustering neural network
    Kulkarni, UV
    Sontakke, TR
    Kulkarni, AB
    [J]. ELECTRONICS LETTERS, 2001, 37 (05) : 301 - 303
  • [4] Modular fuzzy hyperline segment neural network
    Patil, PM
    Kulkarni, UV
    Sontakke, TR
    [J]. PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 1939 - 1944
  • [5] Extended fuzzy hyperline-segment neural network with classification rule extraction
    Shinde, Swati
    Kulkarni, Uday
    [J]. NEUROCOMPUTING, 2017, 260 : 79 - 91
  • [6] Modular General Fuzzy Hyperline Segment Neural Network
    Patil, PM
    Deshmukh, MP
    [J]. PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), VOLS 1-5, 2005, : 1912 - 1917
  • [7] The association of genetic algorithm and fuzzy neural network in handwritten character recognition
    Bac, LH
    Thai, LH
    [J]. KNOWLEDGE-BASED INTELLIGENT INFORMATION ENGINEERING SYSTEMS & ALLIED TECHNOLOGIES, PTS 1 AND 2, 2001, 69 : 1538 - 1544
  • [8] Supervised feedforward fuzzy artificial neural network for handwritten alphanumeric character recognition
    Annadurai, S
    Balasubramaniam, A
    [J]. ELECTRONICS LETTERS, 1996, 32 (21) : 1987 - 1989
  • [9] Handwritten character recognition by a layered neural network
    Zhu, Xiao-Yan
    Yamauchi, Koichiro
    Jimbo, Takashi
    Umeno, Masayoshi
    [J]. Systems and Computers in Japan, 1990, 21 (13) : 88 - 97
  • [10] Modified Fuzzy Hyperline-Segment Neural Network for Classification with Mixed Attribues
    Shinde, S. V.
    Kulkarni, U. V.
    [J]. 2014 INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION AND NETWORKING TECHNOLOGIES (ICCCNT, 2014,
12345