Training an Arabic handwriting recognizer without a handwritten training data set

被引：0

作者：

Ahmad, Irfan ^{[1
,2
]}

Fink, Gernot A. ^{[2
]}

机构：

[1] KFUPM, Informat & Comp Sci Dept, Dhahran, Saudi Arabia

[2] TU Dortmund Univ, Dept Comp Sci, Dortmund, Germany

来源：

2015 13TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR) | 2015年

关键词：

Handwritten text recognition; hidden Markov models; training data; efficient training; HMM adaptation; OCR; ADAPTATION; MODELS;

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：

Handwritten text recognition is an active research area in pattern recognition. One of the prerequisites of setting up a handwritten text recognizer is to train them using, mostly, large amounts of labeled training data. In the current paper we report our work on handwritten text recognition using no handwritten training set. We investigate different approaches including, computer generated text in different typefaces as training data, unsupervised adaptation, and using recognition hypothesis on the test sets as training data. Results from handwritten Arabic word recognition task show that the approach is promising with good recognition rates.

引用

页码：476 / 480

页数：5

共 50 条

[31] Detecting OOV Names in Arabic Handwritten Data
Chen, Jinying
Prasad, Rohit
Cao, Huaigu
Natarajan, Premkumar
2013 12TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2013, : 994 - 998
[32] Deep Learning-Based Child Handwritten Arabic Character Recognition and Handwriting Discrimination
Alwagdani, Maram Saleh
Jaha, Emad Sami
SENSORS, 2023, 23 (15)
[33] TRAINING, CERTIFICATION, AND EXPERIENCE OF HANDWRITING ANALYSTS
PEEPLES, EE
PERCEPTUAL AND MOTOR SKILLS, 1990, 70 (03) : 1219 - 1226
[34] Haptic handwriting aid for training and rehabilitation
Mullins, J
Mawson, C
Nahavandi, S
INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOL 1-4, PROCEEDINGS, 2005, : 2690 - 2694
[35] Handwriting Image Generation by Adversarial Training
Chang, Dan
Xie, Wentao
Yu, Zhiqi
2021 3RD INTERNATIONAL CONFERENCE ON MACHINE LEARNING, BIG DATA AND BUSINESS INTELLIGENCE (MLBDBI 2021), 2021, : 658 - 661
[36] Training without training data: Improving the generalizability of automated medical abbreviation disambiguation
Skreta, Marta
Arbabi, Aryan
Wang, Jixuan
Brudno, Michael
MACHINE LEARNING FOR HEALTH WORKSHOP, VOL 116, 2019, 116 : 233 - 245
[37] Detection of Backdoors in Trained Classifiers Without Access to the Training Set
Xiang, Zhen
Miller, David J.
Kesidis, George
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (03) : 1177 - 1191
[38] Mispronunciation Detection without Nonnative Training Data
Lee, Ann
Glass, James
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 643 - 647
[39] Generation of synthetic training data for an HMM-based handwriting recognition system
Varga, T
Bunke, H
SEVENTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2003, : 618 - 622
[40] Guided construction of training data set for neural networks
Laxdal, EM
Parra-Hernandez, R
Dimopoulos, NJ
2004 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOLS 1-7, 2004, : 5905 - 5910

← 1 2 3 4 5 →