Offline recognition of omnifont Arabic text using the HMM ToolKit (HTK)

被引：46
|
作者：
Khorsheed, M. S. [1 ]
机构：
[1] King Abdulaziz Univ Sci & Technol, Riyadh 11442, Saudi Arabia
来源：
PATTERN RECOGNITION LETTERS | 2007年 / 28卷 / 12期
关键词：
document analysis; pattern analysis and recognition; machine vision; Arabic OCR; HTK;
D O I：
10.1016/j.patrec.2007.03.014
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 presents a cursive Arabic text recognition system. The system decomposes the document image into text line images and extracts a set of simple statistical features from a narrow window which is sliding a long that text line. It then injects the resulting feature vectors to the Hidden Markov Model Toolkit (HTK). HTK is a portable toolkit for speech recognition system. The proposed system is applied to a data corpus which includes Arabic text of more than 600 A4-size sheets typewritten in multiple computer-generated fonts. (c) 2007 Elsevier B.V. All rights reserved.
引用
收藏
页码：1563 / 1571
页数：9
相关论文
共 50 条
  • [31] Arabic Word Decomposition Techniques for Offline Arabic Text Transcription
    BenZeghiba, Mohammed Faouzi
    2017 1ST INTERNATIONAL WORKSHOP ON ARABIC SCRIPT ANALYSIS AND RECOGNITION (ASAR), 2017, : 31 - 35
  • [32] An approach to offline Arabic Character recognition using neural networks
    Nawaz, SN
    Sarfraz, M
    Zidouri, A
    Al-Khatib, WG
    ICECS 2003: PROCEEDINGS OF THE 2003 10TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS AND SYSTEMS, VOLS 1-3, 2003, : 1328 - 1331
  • [33] An approach to offline Arabic character recognition using neural networks
    1600, Emirates Telecommunications Corporation (ETISALAT); Etisalat College of Engineering (ECE); IEEE Circuits and Systems Society (CAS); Institute of Electrical and Electronics Engineers (IEEE); University of Sharjah (UOS) (Institute of Electrical and Electronics Engineers Inc., United States):
  • [34] Offline Arabic handwriting recognition: A survey
    Lorigo, LM
    Govindaraju, V
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (05) : 712 - 724
  • [35] Offline Arabic character recognition system
    黄建华
    唐降龙
    Journal of Harbin Institute of Technology(New series), 2003, (01) : 80 - 88
  • [36] KHATT: Arabic Offline Handwritten Text Database
    Mahmoud, Sabri A.
    Ahmad, Irfan
    Alshayeb, Mohammad
    Al-Khatib, Wasfi G.
    Parvez, Mohammad Tanvir
    Fink, Gernot A.
    Maergner, Volker
    El Abed, Haikal
    13TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR 2012), 2012, : 449 - 454
  • [37] Arabic phonemes recognition using hybrid LVQ/HMM model for continuous speech recognition
    Nahar, Khalid M. O.
    Abu Shquier, Mohammed
    Al-Khatib, Wasfi G.
    Al-Muhtaseb, Husni
    Elshafei, Moustafa
    INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2016, 19 (03) : 495 - 508
  • [38] Multifont Arabic characters recognition using houghtransform and HMM/ANN classification
    National Engineering School of Tunis, Tunisia
    不详
    J. Multimedia, 2006, 2 (50-54):
  • [39] HMM-Based Arabic Sign Language Recognition Using Kinect
    Sarhan, Noha A.
    El-Sonbaty, Yasser
    Youssef, Sherine M.
    2015 TENTH INTERNATIONAL CONFERENCE ON DIGITAL INFORMATION MANAGEMENT (ICDIM), 2015, : 134 - 139
  • [40] Robust Front-End based on MVA and HEQ post-processing for Arabic Speech Recognition Using Hidden Markov Model Toolkit(HTK)
    Techini, Elhem
    Sakka, Zied
    Bouhlel, MedSalim
    2017 IEEE/ACS 14TH INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS AND APPLICATIONS (AICCSA), 2017, : 815 - 820
12345