ASAR 2021 Competition on Online Arabic Word Recognition

被引:0
作者
Akouaydi, Hanen [1 ]
Boubaker, Houcine [1 ]
Njah, Sourour [1 ]
Zaied, Mourad [2 ]
Alimi, Adel M. [1 ,3 ]
机构
[1] Univ Sfax, Natl Engn Sch Sfax ENIS, REGIM Lab REs Grp Intelligent Machines, BP 1173, Sfax, Tunisia
[2] Univ Gabes, Natl Sch Engineers Gabes ENIG, Res Team Intelligent Machines, BP 6072, Gabes, Tunisia
[3] Univ Johannesburg, Fac Engn & Built Environm, Dept Elect & Elect Engn Sci, Johannesburg, South Africa
来源
DOCUMENT ANALYSIS AND RECOGNITION, ICDAR 2021 WORKSHOPS, PT I | 2021年 / 12916卷
关键词
Online Arabic handwritten words; Recognition; Competition;
D O I
10.1007/978-3-030-86198-8_28
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 the Online Arabic words recognition competition (OAWRC 2021) held at ASAR 2021 workshop in conjuction with ICDAR 2021. This competition uses the ADAB database, which is a database of Arabic handwritten words. Three groups with four systems are participating in the competition this year. A brief description of participating systems and the experimental results is doing. The systems were tested on unknown set to the participants of 100 labels. In particular, we wish to investigate and compare participating methods that can be robust against competition challenges. The main goal of this competition is to encourage the research in Arabic script and the development of Arabic handwritten systems. Within good recognition rate, the competition has two new challenges: working with small training set and being robust against noise. The evaluation process of participating systems adapts various metrics such as the recognition rate, the speed, etc. All systems produce good results. The winner and his runner-up are very close while they use different methods.
引用
收藏
页码:390 / 401
页数:12
相关论文
共 39 条
[1]  
Abed H., 2010, INT C DOC AN REC, P1
[2]  
Akouaydi H., 2019, ARXIV PREPRINT ARXIV, V5, P1
[3]   Convolutional Neural Networks for Online Arabic Characters Recognition with Beta-Elliptic Knowledge Domain [J].
Akouaydi, Hanen ;
Njah, Sourour ;
Ouarda, Wael ;
Samet, Anis ;
Zaied, Mourad ;
Alimi, Adel M. .
2019 INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION WORKSHOPS (ICDARW) AND 3RD INTERNATIONAL WORKSHOP ON ARABIC AND DERIVED SCRIPT ANALYSIS AND RECOGNITION (ASAR 2019), VOL 6, 2019, :41-46
[4]  
Akouaydi H, 2017, 2017 1ST INTERNATIONAL WORKSHOP ON ARABIC SCRIPT ANALYSIS AND RECOGNITION (ASAR), P153, DOI 10.1109/ASAR.2017.8067778
[5]  
Alimi AM, 1997, PROC INT CONF DOC, P382, DOI 10.1109/ICDAR.1997.619875
[6]   Generation and analysis of handwriting script with the beta-elliptic model [J].
Bezine, H ;
Alimi, AM ;
Sherkat, N .
NINTH INTERNATIONAL WORKSHOP ON FRONTIERS IN HANDWRITING RECOGNITION, PROCEEDINGS, 2004, :515-520
[7]  
Boubaker H., 2012, ONLINE ARABIC DATABA, P541
[8]   Fast multi-language LSTM-based online handwriting recognition [J].
Carbune, Victor ;
Gonnet, Pedro ;
Deselaers, Thomas ;
Rowley, Henry A. ;
Daryin, Alexander ;
Calvo, Marcos ;
Wang, Li-Lun ;
Keysers, Daniel ;
Feuz, Sandro ;
Gervais, Philippe .
INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2020, 23 (02) :89-102
[9]  
Dhieb T., 2019, Computer Methods in Biomechanics and Biomedical Engineering, V22, P188, DOI 10.1080/10255842.2020.1714235
[10]  
Dhieb T., 2018, ONLINE WRITER IDENTI, P12