Effective Multiple-features Extraction for Off-line SVM-Based Handwritten Numeral Recognition

被引：0
|
作者：
Lee, Shen-Wei [1 ]
Wu, Hsien-Chu [1 ]
机构：
[1] Natl Taichung Univ Sci & Technol, Dept Comp Sci & Informat Engn, Taichung, Taiwan
来源：
THIRD INTERNATIONAL CONFERENCE ON INFORMATION SECURITY AND INTELLIGENT CONTROL (ISIC 2012) | 2012年
关键词：
image recognition; image preprocessing; offline handwritten number; feature extraction; SVM;
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：
In this paper, a multiple features extraction technique for the recognition of handwritten numbers is proposed. The proposed technique mainly extracts direction information from the structure of contours of each handwritten number and the direction information is integrated with a technique for detecting transitions among pixels and counting the number of cross lines in the lined image of offline handwritten numbers. The combinational technique used in the recognition with a Support Vector Machine (SVM) [13] classifier provides recognition rates up to 98.99%. This proposed technique also uses SVM for determining the effective features extracted from the multiple features extraction of the handwritten number recognition.
引用
收藏
页码：194 / 197
页数：4
相关论文
共 50 条
  • [21] Feature extraction and normalization in SVM-based speaker recognition
    Mazibuko, Thembisile
    Mashao, Daniel
    WMSCI 2006: 10TH WORLD MULTI-CONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL V, PROCEEDINGS, 2006, : 260 - +
  • [22] Off-Line Handwritten Arabic Word Recognition Using SVMs with Normalized Poly Kernel
    Alalshekmubarak, Abdulrahman
    Hussain, Amir
    Wang, Qiu-Feng
    NEURAL INFORMATION PROCESSING, ICONIP 2012, PT II, 2012, 7664 : 85 - 91
  • [23] Off-line Handwritten Character Recognition using Hidden Markov Model
    Gayathri, P.
    Ayyappan, Sonal
    2014 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI), 2014, : 518 - 523
  • [24] Histogram of oriented gradients based off-line handwritten devanagari characters recognition using SVM, K-NN and NN classifiers
    Deore S.P.
    Pravin A.
    Revue d'Intelligence Artificielle, 2019, 33 (06) : 441 - 446
  • [25] Performance analysis of single classifier in recognition of off-line handwritten amount in words based on HMM
    Wang Xian-mei
    Lin Zi-yu
    PROCEEDINGS OF 2006 CHINESE CONTROL AND DECISION CONFERENCE, 2006, : 343 - +
  • [26] New off-line Handwritten Signature Verification method based on Artificial Immune Recognition System
    Serdouk, Yasmine
    Nemmour, Hassiba
    Chibani, Youcef
    EXPERT SYSTEMS WITH APPLICATIONS, 2016, 51 : 186 - 194
  • [27] Applied some new features in off-line recognition of totally unconstrained handwritten numerals using neural network
    Dong, L
    Chen, XX
    Wu, SP
    Tang, YY
    1997 IEEE INTERNATIONAL CONFERENCE ON INTELLIGENT PROCESSING SYSTEMS, VOLS 1 & 2, 1997, : 392 - 395
  • [28] Handwritten Digit Recognition based on DCT features and SVM Classifier
    El Qacimy, Bouchra
    Kerroum, Mounir Ait
    Hammouch, Ahmed
    2014 SECOND WORLD CONFERENCE ON COMPLEX SYSTEMS (WCCS), 2014, : 13 - 16
  • [29] Study of Off-Line Handwritten Chinese Character Recognition Based on Dynamic Pruned Binary Tree Svms
    Zhu, Chenghui
    Xu, Xiaoli
    Wang, Jianping
    Xu, Xiaobing
    MATERIALS SCIENCE AND INFORMATION TECHNOLOGY, PTS 1-8, 2012, 433-440 : 3623 - 3628
  • [30] Combining Feature Extraction Methods and Principal Component Analysis for Recognition of Vietnamese Off-Line Handwritten Uppercase Accented Characters
    Thi, Ha Hoang Quoc
    Doan, Mau Hien
    ADVANCES IN COMPUTATIONAL COLLECTIVE INTELLIGENCE (ICCCI 2021), 2021, 1463 : 388 - 398
12345