Hand Gesture Recognition with Symmetric Pattern under Diverse Illuminated Conditions Using Artificial Neural Network
This paper investigated the effects of variant lighting conditions on the recognition process. A framework is proposed to improve the performance of gesture recognition under variant illumination using the luminosity method. To prove the concept, a workable testbed has been developed in the laborato...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-09-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/14/10/2045 |
_version_ | 1797469865454338048 |
---|---|
author | Muhammad Haroon Saud Altaf Shafiq Ahmad Mazen Zaindin Shamsul Huda Sofia Iqbal |
author_facet | Muhammad Haroon Saud Altaf Shafiq Ahmad Mazen Zaindin Shamsul Huda Sofia Iqbal |
author_sort | Muhammad Haroon |
collection | DOAJ |
description | This paper investigated the effects of variant lighting conditions on the recognition process. A framework is proposed to improve the performance of gesture recognition under variant illumination using the luminosity method. To prove the concept, a workable testbed has been developed in the laboratory by using a Microsoft Kinect sensor to capture the depth images for the purpose of acquiring diverse resolution data. For this, a case study was formulated to achieve an improved accuracy rate in gesture recognition under diverse illuminated conditions. For data preparation, American Sign Language (ASL) was used to create a dataset of all twenty-six signs, evaluated in real-time under diverse lighting conditions. The proposed method uses a set of symmetric patterns as a feature set in order to identify human hands and recognize gestures extracted through hand perimeter feature-extraction methods. A Scale-Invariant Feature Transform (SIFT) is used in the identification of significant key points of ASL-based images with their relevant features. Finally, an Artificial Neural Network (ANN) trained on symmetric patterns under different lighting environments was used to classify hand gestures utilizing selected features for validation. The experimental results showed that the proposed system performed well in diverse lighting effects with multiple pixel sizes. A total aggregate 97.3% recognition accuracy rate is achieved across 26 alphabet datasets with only a 2.7% error rate, which shows the overall efficiency of the ANN architecture in terms of processing time. |
first_indexed | 2024-03-09T19:27:05Z |
format | Article |
id | doaj.art-af5476a003284a6986cae7fbad3f1dcf |
institution | Directory Open Access Journal |
issn | 2073-8994 |
language | English |
last_indexed | 2024-03-09T19:27:05Z |
publishDate | 2022-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Symmetry |
spelling | doaj.art-af5476a003284a6986cae7fbad3f1dcf2023-11-24T02:51:19ZengMDPI AGSymmetry2073-89942022-09-011410204510.3390/sym14102045Hand Gesture Recognition with Symmetric Pattern under Diverse Illuminated Conditions Using Artificial Neural NetworkMuhammad Haroon0Saud Altaf1Shafiq Ahmad2Mazen Zaindin3Shamsul Huda4Sofia Iqbal5University Institute of Information Technology, Pir Mehr Ali Shah Arid Agriculture University, Rawalpindi 46300, PakistanUniversity Institute of Information Technology, Pir Mehr Ali Shah Arid Agriculture University, Rawalpindi 46300, PakistanIndustrial Engineering Department, College of Engineering, King Saud University, Riyadh 11421, Saudi ArabiaDepartment of Statistics and Operations Research, College of Science, King Saud University, Riyadh 11451, Saudi ArabiaSchool of Information Technology, Deakin University, Burwood, VIC 3128, AustraliaSpace and Upper Atmosphere Research Commission, Islamabad 44000, PakistanThis paper investigated the effects of variant lighting conditions on the recognition process. A framework is proposed to improve the performance of gesture recognition under variant illumination using the luminosity method. To prove the concept, a workable testbed has been developed in the laboratory by using a Microsoft Kinect sensor to capture the depth images for the purpose of acquiring diverse resolution data. For this, a case study was formulated to achieve an improved accuracy rate in gesture recognition under diverse illuminated conditions. For data preparation, American Sign Language (ASL) was used to create a dataset of all twenty-six signs, evaluated in real-time under diverse lighting conditions. The proposed method uses a set of symmetric patterns as a feature set in order to identify human hands and recognize gestures extracted through hand perimeter feature-extraction methods. A Scale-Invariant Feature Transform (SIFT) is used in the identification of significant key points of ASL-based images with their relevant features. Finally, an Artificial Neural Network (ANN) trained on symmetric patterns under different lighting environments was used to classify hand gestures utilizing selected features for validation. The experimental results showed that the proposed system performed well in diverse lighting effects with multiple pixel sizes. A total aggregate 97.3% recognition accuracy rate is achieved across 26 alphabet datasets with only a 2.7% error rate, which shows the overall efficiency of the ANN architecture in terms of processing time.https://www.mdpi.com/2073-8994/14/10/2045American Sign Languagegesture recognitionvariant lighting conditionssymmetric patternaccuracy |
spellingShingle | Muhammad Haroon Saud Altaf Shafiq Ahmad Mazen Zaindin Shamsul Huda Sofia Iqbal Hand Gesture Recognition with Symmetric Pattern under Diverse Illuminated Conditions Using Artificial Neural Network Symmetry American Sign Language gesture recognition variant lighting conditions symmetric pattern accuracy |
title | Hand Gesture Recognition with Symmetric Pattern under Diverse Illuminated Conditions Using Artificial Neural Network |
title_full | Hand Gesture Recognition with Symmetric Pattern under Diverse Illuminated Conditions Using Artificial Neural Network |
title_fullStr | Hand Gesture Recognition with Symmetric Pattern under Diverse Illuminated Conditions Using Artificial Neural Network |
title_full_unstemmed | Hand Gesture Recognition with Symmetric Pattern under Diverse Illuminated Conditions Using Artificial Neural Network |
title_short | Hand Gesture Recognition with Symmetric Pattern under Diverse Illuminated Conditions Using Artificial Neural Network |
title_sort | hand gesture recognition with symmetric pattern under diverse illuminated conditions using artificial neural network |
topic | American Sign Language gesture recognition variant lighting conditions symmetric pattern accuracy |
url | https://www.mdpi.com/2073-8994/14/10/2045 |
work_keys_str_mv | AT muhammadharoon handgesturerecognitionwithsymmetricpatternunderdiverseilluminatedconditionsusingartificialneuralnetwork AT saudaltaf handgesturerecognitionwithsymmetricpatternunderdiverseilluminatedconditionsusingartificialneuralnetwork AT shafiqahmad handgesturerecognitionwithsymmetricpatternunderdiverseilluminatedconditionsusingartificialneuralnetwork AT mazenzaindin handgesturerecognitionwithsymmetricpatternunderdiverseilluminatedconditionsusingartificialneuralnetwork AT shamsulhuda handgesturerecognitionwithsymmetricpatternunderdiverseilluminatedconditionsusingartificialneuralnetwork AT sofiaiqbal handgesturerecognitionwithsymmetricpatternunderdiverseilluminatedconditionsusingartificialneuralnetwork |