An HMM-based OCR for Persian/Arabic texts

被引：0

作者：

Ahmadi, A ^{[1
]}

Omatu, S ^{[1
]}

Yoshioka, M ^{[1
]}

机构：

[1] Osaka Prefecture Univ, Div Comp & Syst Sci, Dept Engn, Sakai, Osaka 5998531, Japan

来源：

KNOWLEDGE-BASED INTELLIGENT INFORMATION ENGINEERING SYSTEMS & ALLIED TECHNOLOGIES, PTS 1 AND 2 | 2001年 / 69卷

关键词：

OCR; Persian; Arabic; HMM; character recognition; word recognition;

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：

We present a system for recognition of Persian/Arabic texts using hidden Markov model (HMM) in the character level classification. The text is segmented to words at first and from words to characters. A Shadow coding mask are used for extracting the features of characters. Then a Self-Organization Map is employed for clustering the features and reducing the size of inputs. Finally by using the MW classifier and a level building algorithm the words will be composed through recognized characters, The system is evaluated with 10 pages of Persian printed texts and the mean correct classification rate is 95.1% in word level and 99.4% in character level.

引用

页码：824 / 828

页数：5

共 50 条

[31] HMM-based monitoring of packet channels
Rossi, PS
Palmieri, F
Iannello, G
[J]. HIGH SPEED NETWORKS AND MULTIMEDIA COMMUNICATIONS, PROCEEDINGS, 2004, 3079 : 144 - 154
[32] Czech HMM-Based Speech Synthesis
Hanzlicek, Zdenek
[J]. TEXT, SPEECH AND DIALOGUE, 2010, 6231 : 291 - 298
[33] An HMM-based speech recognition IC
Han, W
Hon, KW
Chan, CF
Lee, T
Choy, CS
Pun, KP
Ching, PC
[J]. PROCEEDINGS OF THE 2003 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOL II: COMMUNICATIONS-MULTIMEDIA SYSTEMS & APPLICATIONS, 2003, : 744 - 747
[34] EVALUATION OF HMM-BASED LAUGHTER SYNTHESIS
Urbain, Jerome
Cakmak, Huseyin
Dutoit, Thierry
[J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7835 - 7839
[35] HMM-based multiresolution image segmentation
Lu, JL
Carin, L
[J]. 2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 3357 - 3360
[36] A design for HMM-based SAR ATR
Kottke, DP
Fiore, PD
Brown, KL
Fwu, JK
[J]. ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY V, 1998, 3370 : 541 - 551
[37] HMM-Based Vietnamese Speech Synthesis
Trinh, Son
Hoang, Kiem
[J]. INTERNATIONAL JOURNAL OF SOFTWARE INNOVATION, 2015, 3 (04) : 33 - 47
[38] Treating children in medieval Arabic and Persian medical texts
Katouzian-Safadi, Mehrnaz
Bensaad, Meyssa
Izard, Jean-Philippe
[J]. ANNALES DE BRETAGNE ET DES PAYS DE L OUEST, 2017, 124 (03) : 203 - 227
[39] HMM-based Offline Arabic Handwriting Recognition Using new Feature Extraction and Lexicon Ranking Techniques
Eraqi, Hesham M.
Abdelazeem, Sherif
[J]. 13TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR 2012), 2012, : 554 - 559
[40] TCBR-HMM: An HMM-based text classifier with a CBR system
Borrajo, L.
Seara Vieira, A.
Iglesias, E. L.
[J]. APPLIED SOFT COMPUTING, 2015, 26 : 463 - 473

← 1 2 3 4 5 →