Arabic Sign Language Recognition Using Deep Learning Models

被引：2

作者：

Al-Barham, Muhammad ^{[1
]}

Abu Sa'aleek, Ahmad ^{[1
]}

Al-Odat, Mohammad ^{[1
]}

Hamad, Ghada ^{[1
]}

Al-Yaman, Musa ^{[1
]}

Elnagar, Ashraf ^{[2
]}

机构：

[1] Univ Jordan, Amman, Jordan

[2] Univ Sharjah, Sharjah, U Arab Emirates

来源：

2022 13TH INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION SYSTEMS (ICICS) | 2022年

关键词：

Arabic Sign Language (ArSL); Convolutional Neural Network (CNN); Image Classification; Deep Learning; Transfer Learning;

D O I：

10.1109/ICICS55353.2022.9811162

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Arabic Sign Language (ArSL) is a family of sign languages that are spread throughout the Arab world. This paper focuses on developing a robust deep learning model that is trained on the ArSL2018 dataset to convert images of the ArSL alphabets into Arabic alphabets. The ArSL2018 dataset consists of 54,049 images of 32 alphabets collected from 40 signers. We have implemented and validated several deep learning models, including Convolutional Neural Network (CNN), VGG-16, and ResNet-18. The best result is attained by the modified ResNet-18 model which achieved an average test accuracy of 99.47%.

引用

页码：226 / 231

页数：6

共 18 条

[1] Recognition of gestures in Arabic sign language using neuro-fuzzy systems [J].

Al-Jarrah, O ;

Halawani, A .

ARTIFICIAL INTELLIGENCE, 2001, 133 (1-2) :117-138

[2]

Alani A A., 2021, Indonesian Journal of Electrical Engineering and Computer Science, V22, P1096, DOI [10.11591/ijeecs.v22.i2.pp1096-1107, DOI 10.11591/IJEECS.V22.I2.PP1096-1107]

[3]

Alzohairi R, 2018, INT J ADV COMPUT SC, V9, P185

[4] Multi-modality-based Arabic sign language recognition [J].

Elpeltagy, Marwa ;

Abdelwahab, Moataz ;

Hussein, Mohamed E. ;

Shoukry, Amin ;

Shoala, Asmaa ;

Galal, Moustafa .

IET COMPUTER VISION, 2018, 12 (07) :1031-1039

[5]

Goodfellow I, 2016, ADAPT COMPUT MACH LE, P1

[6] Multiple Proposals for Continuous Arabic Sign Language Recognition [J].

Hassan, Mohamed ;

Assaleh, Khaled ;

Shanableh, Tamer .

SENSING AND IMAGING, 2019, 20 (1)

[7]

Hayat Shoaib, 2019, 2019 IEEE 2nd International Conference on Electronics Technology (ICET), P1, DOI 10.1109/ELTECH.2019.8839402

[8] ArSign: Toward a Mobile Based Arabic Sign Language Translator Using LMC [J].

Kammoun, Slim ;

Darwish, Dawlat ;

Althubeany, Hanan ;

Alfulh, Reem .

UNIVERSAL ACCESS IN HUMAN-COMPUTER INTERACTION. APPLICATIONS AND PRACTICE, UAHCI 2020, PT II, 2020, 12189 :92-101

[9]

Latif G., 2021, Journal of Physics: Conference Series, V1962

[10]

Latif G., 2020, International Journal of Computing and Digital Systems, V9, P715, DOI DOI 10.12785/IJCDS/090418

← 1 2 →