Hand Gesture Recognition for Disabled People Using Bayesian Optimization with Transfer Learning

作     者：Fadwa Alrowais Radwa Marzouk Fahd N.Al-Wesabi Anwer Mustafa Hilal 

作者机构：Department of Computer SciencesCollege of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information SystemsCollege of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of MathematicsFaculty of ScienceCairo UniversityGiza12613Egypt Department of Computer ScienceCollege of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Computer and Self DevelopmentPreparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia 

出 版 物：《Intelligent Automation & Soft Computing》 (智能自动化与软计算（英文）)

年 卷 期：2023年第36卷第6期

页      面：3325-3342页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：The authors extend their appreciation to the King Salman centre for Disability Research for funding this work through Research Group no KSRG-2022-017 

主　　题：Deep learning hand gesture recognition disabled people computer vision bayesian optimization 

摘      要：Sign language recognition can be treated as one of the efficient solu-tions for disabled people to communicate with *** helps them to convey the required data by the use of sign language with no *** latest develop-ments in computer vision and image processing techniques can be accurately uti-lized for the sign recognition process by disabled *** Sign Language(ASL)detection was challenging because of the enhancing intraclass similarity and higher *** article develops a new Bayesian Optimiza-tion with Deep Learning-Driven Hand Gesture Recognition Based Sign Language Communication(BODL-HGRSLC)for Disabled *** BODL-HGRSLC technique aims to recognize the hand gestures for disabled people’s *** presented BODL-HGRSLC technique integrates the concepts of compu-ter vision(CV)and DL *** the presented BODL-HGRSLC technique,a deep convolutional neural network-based residual network(ResNet)model is applied for feature ***,the presented BODL-HGRSLC model uses Bayesian optimization for the hyperparameter tuning *** last,a bidir-ectional gated recurrent unit(BiGRU)model is exploited for the HGR procedure.A wide range of experiments was conducted to demonstrate the enhanced perfor-mance of the presented BODL-HGRSLC *** comprehensive comparison study reported the improvements of the BODL-HGRSLC model over other DL models with maximum accuracy of 99.75%.