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
  • [41] Zone-Based Hybrid Feature Extraction Algorithm for Handwritten Numeral Recognition of Four Indian Scripts
    Rajashekararadhya, S. V.
    Ranjan, Vanaja P.
    2009 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2009), VOLS 1-9, 2009, : 5145 - 5150
  • [42] Performance Evaluation of MLP and RBF Feed Forward Neural Network for the Recognition of Off-Line Handwritten Characters.
    Rishi, Rahul
    Choudhary, Amit
    Singh, Ravinder
    Dhaka, Vijaypal Singh
    Ahlawat, Savita
    Rao, Mukta
    SECOND INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING, 2010, 7546
  • [43] Multiclass SVM-based Language-Independent Emotion Recognition using Selective Speech Features
    Amol, Kokane T.
    Guddeti, Ram Mohana Reddy
    2014 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI), 2014, : 1069 - 1073
  • [44] Zone-Based Hybrid Feature Extraction Algorithm for Handwritten Numeral Recognition of Two Popular Indian Scripts
    Rajashekararadhya, S. V.
    Ranjan, Vanaja P.
    2009 WORLD CONGRESS ON NATURE & BIOLOGICALLY INSPIRED COMPUTING (NABIC 2009), 2009, : 525 - 529
  • [45] Hybrid Off-Line Handwritten Signature Verification Based on Artificial Immune Systems and Support Vector Machines
    Serdouk, Yasmine
    Nemmour, Hassiba
    Chibani, Youcef
    IMAGE ANALYSIS AND RECOGNITION (ICIAR 2016), 2016, 9730 : 558 - 565
  • [46] Cracked Tongue Recognition Based on Deep Features and Multiple-Instance SVM
    Xue, Yushan
    Li, Xiaoqiang
    Cui, Qing
    Wang, Lu
    Wu, Pin
    ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2018, PT II, 2018, 11165 : 642 - 652
  • [47] On-line estimation of the aerobic phase length for partial nitrification processes in SBR based on features extraction and SVM classification
    Jaramillo, Francisco
    Orchard, Marcos
    Munoz, Carlos
    Antileo, Christian
    Saez, Doris
    Espinoza, Pablo
    CHEMICAL ENGINEERING JOURNAL, 2018, 331 : 114 - 123
  • [48] A Circular Grid-Based Rotation Invariant Feature Extraction Approach for Off-line Signature Verification
    Parodi, Marianela
    Gomez, Juan C.
    Belaid, Abdel
    11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 1289 - 1293
  • [49] A novel system for off-line 3D seam extraction and path planning based on point cloud segmentation for arc welding robot
    Yang, Lei
    Liu, Yanhong
    Peng, Jinzhu
    Liang, Zize
    ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING, 2020, 64
  • [50] Unconstrained word-based approach for off-line script recognition using density-based random-vector functional-link net
    Park, GH
    Pao, YH
    NEUROCOMPUTING, 2000, 31 (1-4) : 45 - 65
12345