Arab Sign language Recognition with Convolutional Neural Networks

Hayani, Salma; Benaddy, Mohamed; Meslouhi, Othmane El; Kardouchi, Mustapha

doi:10.1109/iccsre.2019.8807586

Cited by 49 publications

(21 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The study of Hayani et al [5] developed a system using convolutional neural networks (CNN), which are multi-layer neural networks that make use of deep learning to analyze images. The proposed model used CNN inspired fbyLeNet-5.…”

Section: Iiii Recognition Methodsmentioning

confidence: 99%

A Saudi Sign Language Recognition System based on Convolutional Neural Networks

Al-Obodi¹,

Al-Hanine²,

Al-Harbi³

et al. 2020

International Journal of Engineering Research and Technology

View full text Add to dashboard Cite

Sign language is the main communication method for deaf people. It is a collection of signs that deaf people use to deal with each other. Deaf people find it difficult to communicate with normal people, as most of them do not understand the signs of the sign language. Sign language recognition systems translate the signs into natural languages and thus shorten the gap between deaf and normal people. Many studies have been done on different sign languages. There is a considerable number of studies on the standard Arabic sign language. In Saudi Arabia, deaf people use the Saudi language, which is different from standard Arabic. This study proposes a smart recognition system for Saudi sign language based on convolutional neural networks. The system is based on the Saudi Sign language dictionary, which was published recently in 2018. In this study, we constructed a dataset of 40 Saudi signs with about 700 images for each sign. We then developed a deep convolutional neural network and trained it on the constructed dataset. To have better recognition, we took images of the signs with different hand sizes, skin colors, lighting, backgrounds, and with/without accessories. The results showed that the recognition model achieved an accuracy of 97.69% for training data and 99.47% for testing data. The model was implemented in two versions: mobile and desktop.

show abstract

Section: Iiii Recognition Methodsmentioning

confidence: 99%

A Saudi Sign Language Recognition System based on Convolutional Neural Networks

Al-Obodi¹,

Al-Hanine²,

Al-Harbi³

et al. 2020

International Journal of Engineering Research and Technology

View full text Add to dashboard Cite

show abstract

“…In addition to the conventional approaches, existing Arabic sign language recognition systems rely on deep learning paradigms which the ability to learn the most relevant features was confirmed in a wide range of applications. In particular, the authors in [32] designed an ArSL alphabet and digits recognition system using convolutional neural networks. Their network inspired by LeNet-5 [6] is composed of two convolutional and Leaky ReLU layers, two Max pooling layer to reduce the image size, one 75% dropout layer to reduce overfitting, and three fully connected layers for classification.…”

Section: Related Workmentioning

confidence: 99%

Arabic Sign Language Recognition using Faster R-CNN

Alawwad¹,

Bchir²,

Ismail³

2021

IJACSA

View full text Add to dashboard Cite

Deafness does not restrict its negative effect on the person's hearing, but rather on all aspect of their daily life. Moreover, hearing people aggravated the issue through their reluctance to learn sign language. This resulted in a constant need for human translators to assist deaf person which represents a real obstacle for their social life. Therefore, automatic sign language translation emerged as an urgent need for the community. The availability and the widespread use of mobile phones equipped with digital cameras promoted the design of image-based Arabic Sign Language (ArSL) recognition systems. In this work, we introduce a new ArSL recognition system that is able to localize and recognize the alphabet of the Arabic sign language using a Faster Region-based Convolutional Neural Network (R-CNN). Specifically, faster R-CNN is designed to extract and map the image features, and learn the position of the hand in a given image. Additionally, the proposed approach alleviates both challenges; the choice of the relevant features used to encode the sign visual descriptors, and the segmentation task intended to determine the hand region. For the implementation and the assessment of the proposed Faster R-CNN based sign recognition system, we exploited VGG-16 and ResNet-18 models, and we collected a real ArSL image dataset. The proposed approach yielded 93% accuracy and confirmed the robustness of the proposed model against drastic background variations in the captured scenes.

show abstract

“…Many researchers have used different methods to identify sign language in general or Arabic, and some of them will be presented. In [7], a method for recognizing ArSL numbers and letters is suggested. With a real dataset of 5839 images of 28 characters and 2030 images of numbers (from 0 to 10), this system is based on CNN.…”

Section: Related Workmentioning

confidence: 99%

Static hand gesture recognition of Arabic sign language by using deep CNNs

Ismail

Dawwd

Ali

2021

IJEECS

View full text Add to dashboard Cite

An Arabic sign language recognition using two concatenated deep convolution neural network models DenseNet121 & VGG16 is presented. The pre-trained models are fed with images, and then the system can automatically recognize the Arabic sign language. To evaluate the performance of concatenated two models in the Arabic sign language recognition, the red-green-blue (RGB) images for various static signs are collected in a dataset. The dataset comprises 220,000 images for 44 categories: 32 letters, 11 numbers (0:10), and 1 for none. For each of the static signs, there are 5000 images collected from different volunteers. The pre-trained models were used and trained on prepared Arabic sign language data. These models were used after some modification. Also, an attempt has been made to adopt two models from the previously trained models, where they are trained in parallel deep feature extractions. Then they are combined and prepared for the classification stage. The results demonstrate the comparison between the performance of the single model and multi-model. It appears that most of the multi-model is better in feature extraction and classification than the single models. And also show that when depending on the total number of incorrect recognize sign image in training, validation and testing dataset, the best convolutional neural networks (CNN) model in feature extraction and classification Arabic sign language is the DenseNet121 for a single model using and DenseNet121 & VGG16 for multi-model using.

show abstract

Arab Sign language Recognition with Convolutional Neural Networks

Cited by 49 publications

References 9 publications

A Saudi Sign Language Recognition System based on Convolutional Neural Networks

A Saudi Sign Language Recognition System based on Convolutional Neural Networks

Arabic Sign Language Recognition using Faster R-CNN

Static hand gesture recognition of Arabic sign language by using deep CNNs

Contact Info

Product

Resources

About