A Time Delay Neural Network for Online Arabic Handwriting Recognition

被引：1

作者：

Zouari, Ramzi ^{[1
]}

Boubaker, Houcine ^{[1
]}

Kherallah, Monji ^{[2
]}

机构：

[1] Univ Sfax, Natl Sch Engn Sfax ENIS, Sfax, Tunisia

[2] Univ Sfax, Fac Sci Sfax, Sfax, Tunisia

来源：

INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS (ISDA 2016) | 2017年 / 557卷

关键词：

Time delay neural network; Beta-elliptic model; Beta impulse; Velocity; Receptive fields; Shared weights;

D O I：

10.1007/978-3-319-53480-0_99

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Handwriting recognition is an interesting part in pattern recognition field. In the last decade, several approaches are focused on online handwriting recognition because the very rapid growth of new technologies in the field of data entry. In this paper, we propose a new system for online Arabic handwriting recognition based on beta-elliptic model which allow to segment the trajectory into segments called strokes by inspecting the extremums points of velocity profile and extract their dynamic and geometric profiles. These strokes are used to train the Time Delay Neural Network (TDNN) which is able to represent the sequential aspect of input data. To evaluate our method, we have used a total of 25000 Arabic letters from the LMCA database. Our experimental results demonstrate the effectiveness of our proposed method and show recognition rates exceeds the 95%.

引用

页码：1005 / 1014

页数：10

共 25 条

[1] Abdelazeem S., 2013, 11 INT C DOC AN REC, P1304
[2] Abdelaziz A, 2015, PATTERN RECOGN LETT, V19, P1129
[3] Bezine H., 2014, 6 INT C ADV COGN TEC, P126
[4] Boubaker H., 2012, Guide to OCR for Arabic Scripts, P541
[5] Boubaker H., 2016, INT J INF ASSUR SECU, V18, P1632
[6] Boubaker H., 2013, INT J COMPUTER SCI I, V10, P57
[7] Boubaker H., 2009, 9 INT C DOC AN REC, V2, P1233
[8] Combining of Off-line and On-line Feature Extraction Approaches for Writer Identification
Chaabouni, Aymen
Boubaker, Houcine
Kherallah, Monji
Alimi, Adel M.
El Abed, Haikal
[J]. 11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 1299 - 1303
[9] Charfi M, 2012, INT J ADV COMPUT SC, V3, P1
[10] Dhieb T, 2015, INT CONF INTELL SYST, P74, DOI 10.1109/ISDA.2015.7489203

← 1 2 3 →