The recognition of handwritten digit strings of unknown length using hidden Markov models

被引:0
作者
Procter, S [1 ]
Illingworth, J [1 ]
Elms, AJ [1 ]
机构
[1] Univ Surrey, Sch Elect Engn Informat Technol & Math, Guildford GU2 5XH, Surrey, England
来源
FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1 AND 2 | 1998年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We apply an HMM-based text recognition system to the recognition of handwritten digit strings of unknown length. The algorithm is tailored to the input data by controlling the maximum number of levels searched by the Level Building (LB) search algorithm. We demonstrate that setting this parameter according to the pixel length of the observation sequence, rather than using a fixed value for all input data, results in a faster and more accurate system. Best results were achieved by setting the maximum number of levels to twice the estimated number of characters in the input string. We also describe experiments which show the potential for further improvement by using an adaptive termination criterion iii the LB search.
引用
收藏
页码:1515 / 1517
页数:3
相关论文
共 50 条
[21]   A hidden Markov model based segmentation and recognition algorithm for chinese handwritten address character strings [J].
Fu, Q ;
Ding, XQ ;
Liu, CS ;
Jiang, Y ;
Ren, Z .
EIGHTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS 1 AND 2, PROCEEDINGS, 2005, :590-594
[22]   Recognition of Cursive Arabic Handwritten Text Using Embedded Training Based on Hidden Markov Models [J].
Rabi, Mouhcine ;
Amrouch, Mustapha ;
Mahani, Zouhir .
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2018, 32 (01)
[23]   Off-line recognition of handwritten Arabic words using multiple Hidden Markov Models [J].
Alma'adeed, S ;
Higgins, C ;
Elliman, D .
RESEARCH AND DEVELOPMENT IN INTELLIGENT SYSTEMS XX, 2004, :33-40
[24]   Off-line recognition of handwritten Arabic words using multiple hidden Markov models [J].
Alma'adeed, S ;
Higgins, C ;
Elliman, D .
KNOWLEDGE-BASED SYSTEMS, 2004, 17 (2-4) :75-79
[25]   EXPERIMENTS IN SPEAKER-DEPENDENT ISOLATED DIGIT RECOGNITION USING HIDDEN MARKOV-MODELS [J].
RUSSELL, MJ ;
COOK, AE .
PROCEEDINGS : INSTITUTE OF ACOUSTICS, VOL 8, PART 7: SPEECH & HEARING, 1986, 8 :291-298
[26]   Off-line recognition of handwritten Korean and alphanumeric characters using hidden Markov models [J].
Kim, WS ;
Park, RH .
PATTERN RECOGNITION, 1996, 29 (05) :845-858
[27]   Online Thai handwritten character recognition using Hidden Markov Models and Support Vector Machines [J].
Sanguansat, P ;
Asdornwised, W ;
Jitapunkul, S .
IEEE INTERNATIONAL SYMPOSIUM ON COMMUNICATIONS AND INFORMATION TECHNOLOGIES 2004 (ISCIT 2004), PROCEEDINGS, VOLS 1 AND 2: SMART INFO-MEDIA SYSTEMS, 2004, :492-497
[28]   Unconstrained Farsi handwritten word recognition using fuzzy vector quantization and hidden Markov models [J].
Dehghan, M ;
Faez, K ;
Ahmadi, M ;
Shridhar, M .
PATTERN RECOGNITION LETTERS, 2001, 22 (02) :209-214
[29]   Online handwritten signature verification using hidden Markov models [J].
Igarza, JJ ;
Goirizelaia, I ;
Espinosa, K ;
Hernáez, I ;
Méndez, R ;
Sánchez, J .
PROGRESS IN PATTERN RECOGNITION, SPEECH AND IMAGE ANALYSIS, 2003, 2905 :391-399
[30]   Ada-boosting Extreme Learning Machines for Handwritten Digit and Digit Strings Recognition [J].
Saabni, Raid .
2015 FIFTH INTERNATIONAL CONFERENCE ON DIGITAL INFORMATION PROCESSING AND COMMUNICATIONS (ICDIPC), 2015, :231-236