Arabic handwriting text recognition based on efficient segmentation, DCT and HOG features

被引：0
|
作者：
Kadhm M.S. [1 ]
Hassan A.K.A. [1 ]
机构：
[1] Computer Science Department, University of Technology, Baghdad
来源：
International Journal of Multimedia and Ubiquitous Engineering | 2016年 / 11卷 / 10期
关键词：
Arabic text; DCT; Feature extraction; HOG; Segmentation;
D O I：
10.14257/ijmue.2016.11.10.07
中图分类号：
学科分类号：
摘要：
Writing in its different forms, printed and manuscript has always been a tool essential in human communication, and as ubiquitous in most areas of its operations. It is used to store and archive knowledge. Thereby, human has always developed techniques for sustainability across generations. Indeed, with the advent of new information technologies and electronics computers, and further increase the power of machines, automated processing. Besides, one of the important system is the handwriting recognition. Handwriting text recognition system based on efficient segmentation, DCT and HOG Features is proposed. The proposed system depends on the segmentation of the text into words only. Moreover, the system achieved best recognition accuracy 96.317% based on the used methods and SVM classifier. © 2016 SERSC.
引用
收藏
页码：83 / 92
页数：9
相关论文
共 50 条
  • [41] A contour code feature based segmentation for handwriting recognition
    Verma, B
    SEVENTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2003, : 1203 - 1207
  • [42] Improved linear density technique for segmentation in Arabic handwritten text recognition
    Al Hamad, Husam Ahmed
    Abualigah, Laith
    Shehab, Mohammad
    Al-Shqeerat, Khalil H. A.
    Otair, Mohammad
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (20) : 28531 - 28558
  • [43] NEURAL COMPUTING FOR ONLINE ARABIC HANDWRITING RECOGNITION USING HARD STROKE FEATURES MINING
    Rehman, Amjad
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2021, 17 (01): : 177 - 191
  • [44] An Efficient Segmentation Algorithm for Arabic Handwritten Characters Recognition System
    Fadeel, Mohamed A.
    PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON MATHEMATICS AND COMPUTERS IN SCIENCES AND IN INDUSTRY (MCSI 2016), 2016, : 172 - 177
  • [45] An Efficient Segmentation Algorithm for Arabic Handwritten Characters Recognition System
    Ali, Mohamed A.
    AFRO-EUROPEAN CONFERENCE FOR INDUSTRIAL ADVANCEMENT, AECIA 2014, 2015, 334 : 193 - 204
  • [46] Combination of Global and Local Baseline-independent Features for Offline Arabic Handwriting Recognition
    Li, Ning
    Xie, Xudong
    Liu, Wentao
    Lam, Kin-Man
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 713 - 716
  • [47] A Markovian Engine for Text Recognition: Cursive Arabic Text, Statistical Features and Interconnected HMMs
    Khorsheed, M. S.
    Al-Omari, H.
    IMAGE ANALYSIS AND RECOGNITION, PT I, 2012, 7324 : 375 - 381
  • [48] Efficient Segmentation of Arabic Handwritten Characters Using Structural Features
    Bahashwan, Mazen
    Abu-Bakar, Syed
    Sheikh, Usman
    INTERNATIONAL ARAB JOURNAL OF INFORMATION TECHNOLOGY, 2017, 14 (06) : 870 - 879
  • [49] An evolutionary harmony search algorithm with dominant point detection for recognition-based segmentation of online Arabic text recognition
    Potrus, Moayad Yousif
    Ngah, Umi Kalthum
    Ahmed, Bestoun S.
    AIN SHAMS ENGINEERING JOURNAL, 2014, 5 (04) : 1129 - 1139
  • [50] Offline Isolated Arabic Handwriting Character Recognition System Based on SVM
    Salam, Mustafa
    Hassan, Alia Abdul
    INTERNATIONAL ARAB JOURNAL OF INFORMATION TECHNOLOGY, 2019, 16 (03) : 467 - 472
12345