Contractive Autoencoder and SVM for Recognition of Handwritten Devanagari Numerals

被引：0
|
作者：
Kabra, Ruhi R. [1 ]
机构：
[1] MSSs Coll Engn & Technol, Dept Comp Sci & Engn, Jalna, India
来源：
2017 1ST INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND INFORMATION MANAGEMENT (ICISIM) | 2017年
关键词：
Contractive autoencoder; SVM; Handwritten numerals 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：
Representation of data is very important in case of machine learning. Better the representation, the classifiers will give better results. Contractive autoencoders are used to learn the representation of data which are robust to small changes in the input. This paper uses contractive autoencoder and SVM classifier for handwritten Devanagari numerals recognition. The accuracy obtained using CAE+SVM is 96 %.
引用
收藏
页码：26 / 29
页数：4
相关论文
共 50 条
  • [31] A recognition system for Devnagri and English handwritten numerals
    Lehal, GS
    Bhatt, N
    ADVANCES IN MULTIMODAL INTERFACES - ICMI 2000, PROCEEDINGS, 2000, 1948 : 442 - 449
  • [32] Recognition of handwritten numerals based on structural features
    Liu, Huichun
    Ma, Shuyuan
    Wu, Pingdong
    Yang, Feng
    Zeng, Xingsheng
    Bi, Luzheng
    Jisuanji Gongcheng/Computer Engineering, 2002, 28 (11):
  • [33] A hybrid approach to unconstrained handwritten numerals recognition
    Wang, S
    Shu, C
    Xia, SW
    ICSP '96 - 1996 3RD INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, PROCEEDINGS, VOLS I AND II, 1996, : 1334 - 1337
  • [34] REAL-TIME RECOGNITION OF HANDWRITTEN NUMERALS
    IMPEDOVO, S
    MARANGELLI, B
    PLANTAMURA, VL
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1976, 6 (02): : 145 - 148
  • [35] COMPUTER RECOGNITION OF HANDWRITTEN NUMERALS BY POLYGONAL APPROXIMATIONS
    PAVLIDIS, T
    ALI, F
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1975, 5 (06): : 610 - 614
  • [36] RECOGNITION OF ISOLATED AND SIMPLY CONNECTED HANDWRITTEN NUMERALS
    SHRIDHAR, M
    BADRELDIN, A
    PATTERN RECOGNITION, 1986, 19 (01) : 1 - 12
  • [37] An SVM-Based high-accurate recognition approach for handwritten numerals by using difference features
    Huang, Kaizhu
    Sun, Jun
    Hotta, Yoshinobu
    Fujimoto, Katsuhito
    Naoi, Satoshi
    ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2007, : 589 - +
  • [38] Handwritten Changma Numerals Recognition Using Capsule Networks
    Hasan, Md Zahid
    Hasan, K. M. Zubair
    Hossain, Shakhawat
    Al Mamun, Abdullah
    Assaduzzaman, Md
    2019 5TH INTERNATIONAL CONFERENCE ON ADVANCES IN ELECTRICAL ENGINEERING (ICAEE), 2019, : 386 - 391
  • [39] Line handwritten Devanagari word recognition: An HMM based approach
    Parui, Swapan Kumar
    Shaw, Bikash
    PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PROCEEDINGS, 2007, 4815 : 528 - 535
  • [40] Rotation Invariance in Transform Features for Handwritten Devanagari Character Recognition
    Shelke, Sushama
    Rege, Priti
    2018 4TH INTERNATIONAL CONFERENCE FOR CONVERGENCE IN TECHNOLOGY (I2CT), 2018,
12345