American Sign Language Recognition Model Using Complex Zernike Moments and Complex-Valued Deep Neural Networks

Technological advancements play a significant role in the integration of deaf and mute individuals into society. Therefore, improvements in sign language recognition systems are of great importance. Many studies on sign languages have been conducted using real numbers. In this paper, a new approach...

Full description

Saved in:
Bibliographic Details
Main Authors: Selda Bayrak, Vasif Nabiyev, Celal Atalar
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10680527/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846108165816451072
author Selda Bayrak
Vasif Nabiyev
Celal Atalar
author_facet Selda Bayrak
Vasif Nabiyev
Celal Atalar
author_sort Selda Bayrak
collection DOAJ
description Technological advancements play a significant role in the integration of deaf and mute individuals into society. Therefore, improvements in sign language recognition systems are of great importance. Many studies on sign languages have been conducted using real numbers. In this paper, a new approach is presented for performing feature extraction from images and sign language alphabet recognition using complex numbers. In this context, a model is developed for recognizing American sign language. In the developed model, complex Zernike moments are used to obtain the feature vector of character images. A complex-valued deep neural network (CVDNN) capable of processing the feature vector composed of complex numbers across layers is also developed. CVDNNs are a powerful method capable of addressing the complex optimization issues of traditional deep neural networks more efficiently. CVDNNs, which use complex numbers as input data and complex activation functions in each layer, are expected to deliver superior performance in fields such as robotic systems, biometric technologies, disease diagnosis, and telecommunications. The model achieves recognition rates of 89.01% on the Sign Language MNIST dataset and 98.67% for holdout and 81.22% for leave-one-subject-out on the Massey University dataset, respectively, without any preprocessing. Our model, which is compared separately with many studies using the same datasets, shows the best performance when the two datasets are considered together. It has been observed that working with complex numbers resulted in a positive impact on performance of approximately 20% compared to configuring our model to work with real numbers while keeping its structure intact.
format Article
id doaj-art-c091d16dc0584f70b8ad94c2b3810249
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c091d16dc0584f70b8ad94c2b38102492024-12-26T00:00:29ZengIEEEIEEE Access2169-35362024-01-011219300119301310.1109/ACCESS.2024.346157210680527American Sign Language Recognition Model Using Complex Zernike Moments and Complex-Valued Deep Neural NetworksSelda Bayrak0https://orcid.org/0000-0003-0240-6592Vasif Nabiyev1https://orcid.org/0000-0003-0314-8134Celal Atalar2https://orcid.org/0000-0003-1932-5289Department of Software Engineering, Karadeniz Technical University, Trabzon, TürkiyeDepartment of Computer Engineering, Karadeniz Technical University, Trabzon, TürkiyeDepartment of Software Engineering, Karadeniz Technical University, Trabzon, TürkiyeTechnological advancements play a significant role in the integration of deaf and mute individuals into society. Therefore, improvements in sign language recognition systems are of great importance. Many studies on sign languages have been conducted using real numbers. In this paper, a new approach is presented for performing feature extraction from images and sign language alphabet recognition using complex numbers. In this context, a model is developed for recognizing American sign language. In the developed model, complex Zernike moments are used to obtain the feature vector of character images. A complex-valued deep neural network (CVDNN) capable of processing the feature vector composed of complex numbers across layers is also developed. CVDNNs are a powerful method capable of addressing the complex optimization issues of traditional deep neural networks more efficiently. CVDNNs, which use complex numbers as input data and complex activation functions in each layer, are expected to deliver superior performance in fields such as robotic systems, biometric technologies, disease diagnosis, and telecommunications. The model achieves recognition rates of 89.01% on the Sign Language MNIST dataset and 98.67% for holdout and 81.22% for leave-one-subject-out on the Massey University dataset, respectively, without any preprocessing. Our model, which is compared separately with many studies using the same datasets, shows the best performance when the two datasets are considered together. It has been observed that working with complex numbers resulted in a positive impact on performance of approximately 20% compared to configuring our model to work with real numbers while keeping its structure intact.https://ieeexplore.ieee.org/document/10680527/Complex valued deep neural networkcomplex Zernike momentsfeature extractionsign language recognition model
spellingShingle Selda Bayrak
Vasif Nabiyev
Celal Atalar
American Sign Language Recognition Model Using Complex Zernike Moments and Complex-Valued Deep Neural Networks
IEEE Access
Complex valued deep neural network
complex Zernike moments
feature extraction
sign language recognition model
title American Sign Language Recognition Model Using Complex Zernike Moments and Complex-Valued Deep Neural Networks
title_full American Sign Language Recognition Model Using Complex Zernike Moments and Complex-Valued Deep Neural Networks
title_fullStr American Sign Language Recognition Model Using Complex Zernike Moments and Complex-Valued Deep Neural Networks
title_full_unstemmed American Sign Language Recognition Model Using Complex Zernike Moments and Complex-Valued Deep Neural Networks
title_short American Sign Language Recognition Model Using Complex Zernike Moments and Complex-Valued Deep Neural Networks
title_sort american sign language recognition model using complex zernike moments and complex valued deep neural networks
topic Complex valued deep neural network
complex Zernike moments
feature extraction
sign language recognition model
url https://ieeexplore.ieee.org/document/10680527/
work_keys_str_mv AT seldabayrak americansignlanguagerecognitionmodelusingcomplexzernikemomentsandcomplexvalueddeepneuralnetworks
AT vasifnabiyev americansignlanguagerecognitionmodelusingcomplexzernikemomentsandcomplexvalueddeepneuralnetworks
AT celalatalar americansignlanguagerecognitionmodelusingcomplexzernikemomentsandcomplexvalueddeepneuralnetworks