PROBABILISTIC ESTIMATION OF BRAILLE DOCUMENT PARAMETERS

被引:2
|
作者
Babadi, Majid Yoosefi [1 ]
Nasihatkon, Behrooz [1 ]
Azimifar, Zohreh [1 ]
Fieguth, Paul [2 ]
机构
[1] Shiraz Univ, Dept Comp Sci & Engn, Shiraz, Iran
[2] Univ Waterloo, Syst Design Engn, Waterloo, ON N2L 3G1, Canada
关键词
Braille; Expectation-Maximization; Line-spacing; Maximum-Likelihood; Skewness;
D O I
10.1109/ICIP.2009.5413816
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Braille is the most common means of reading and study for visually handicapped people. The need for converting Braille documents into a computer-readable format has motivated research into the implementation of Braille recognition systems. The most fundamental steps in such recognition are estimating the scaling, spacing, and skewness properties of a given Braille document. In this paper we propose a statistical method for estimating these parameters, where we model an entire Braille image using a parameterized probability density function and find the maximum-likelihood (ML) estimates using Expectation-Maximization (EM) algorithm. The proposed method is robust against noise and other image artifacts, and has a modest computational complexity for straightforward execution on ordinary personal computers.
引用
收藏
页码:2001 / +
页数:2
相关论文
共 50 条
  • [41] DOCUMENT RETRIEVAL USING A PROBABILISTIC KNOWLEDGE MODEL
    Wang, Shuguang
    Visweswaran, Shyam
    Hauskrecht, Milos
    KDIR 2009: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND INFORMATION RETRIEVAL, 2009, : 26 - +
  • [42] The organisation and visualisation of document corpora:: A probabilistic approach
    Girolami, M
    Vinokourov, A
    Kabán, A
    11TH INTERNATIONAL WORKSHOP ON DATABASE AND EXPERT SYSTEMS APPLICATION, PROCEEDINGS, 2000, : 558 - 564
  • [43] PROBABILISTIC APPROACHES TO THE DOCUMENT-RETRIEVAL PROBLEM
    MARON, ME
    LECTURE NOTES IN COMPUTER SCIENCE, 1983, 146 : 98 - 107
  • [44] Probabilistic document length priors for language models
    Blanco, Roi
    Barreiro, Alvaro
    ADVANCES IN INFORMATION RETRIEVAL, 2008, 4956 : 394 - 405
  • [45] A probabilistic relational approach for web document clustering
    Fersini, E.
    Messina, E.
    Archetti, F.
    INFORMATION PROCESSING & MANAGEMENT, 2010, 46 (02) : 117 - 130
  • [46] A Probabilistic model for compact document topic representation
    Berenyi, Zsolt
    Vajk, Istvan
    PROCEEDINGS OF THE 9TH WSEAS INTERNATIONAL CONFERENCE ON SIMULATION, MODELLING AND OPTIMIZATION, 2009, : 322 - +
  • [47] Probabilistic data fusion on a large document collection
    Lillis, David
    Toolan, Fergus
    Collier, Rem
    Dunnion, John
    ARTIFICIAL INTELLIGENCE REVIEW, 2006, 26 (1-2) : 23 - 34
  • [48] Probabilistic data fusion on a large document collection
    David Lillis
    Fergus Toolan
    Rem Collier
    John Dunnion
    Artificial Intelligence Review, 2006, 26 : 23 - 34
  • [49] PROBABILISTIC AND GENETIC ALGORITHMS FOR DOCUMENT-RETRIEVAL
    GORDON, M
    COMMUNICATIONS OF THE ACM, 1988, 31 (10) : 1208 - 1218
  • [50] ESTIMATION OF THE PARAMETERS OF HIDDEN MARKOV-MODELS OF NOISE-LIKE SIGNALS WITH ABRUPTLY CHANGING PROBABILISTIC PROPERTIES .2. ESTIMATION OF THE STRUCTURAL PARAMETERS OF THE MODEL
    IVANOVA, TO
    MOTTL, VV
    MUCHNIK, IB
    AUTOMATION AND REMOTE CONTROL, 1994, 55 (10) : 1428 - 1445