Gesture recognition and response system for special education using computer vision and human-computer interaction technology
Gesture recognition has emerged as a pivotal technology for enhancing human-computer interaction (HCI), especially in the context of special education. This study presents a comprehensive gesture recognition and response system that leverages advanced deep learning architectures, including AlexNet,...
Saved in:
| Published in: | Disability and rehabilitation: Assistive technology p. 1 |
|---|---|
| Main Author: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
England
08.07.2025
|
| Subjects: | |
| ISSN: | 1748-3115, 1748-3115 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Gesture recognition has emerged as a pivotal technology for enhancing human-computer interaction (HCI), especially in the context of special education. This study presents a comprehensive gesture recognition and response system that leverages advanced deep learning architectures, including AlexNet, VGG19, ResNet and MobileNet, combined with machine learning algorithms such as support vector machines (SVM) and random forest. The proposed system achieves state-of-the-art performance, with an accuracy of 95.4%, demonstrating its effectiveness in recognising complex gestures with high precision. To address the challenges of deploying gesture recognition systems on resource-constrained devices, the study incorporates genetic algorithms (GAs) for model compression. This optimisation reduces the model size by 42%, significantly enhancing its suitability for real-time applications on mobile and embedded platforms. Additionally, inference time is reduced by 45%, enabling faster response times essential for interactive educational environments. The system was evaluated using a diverse gesture dataset, ensuring robustness across varying lighting conditions, user demographics, and physical differences. The findings highlight the potential of integrating gesture recognition systems into special education, where they can serve as assistive tools for individuals with disabilities, fostering inclusive and engaging learning experiences. This work not only advances the field of gesture recognition but also underscores the importance of model optimisation for real-world applications. Future research will focus on expanding the gesture library, integrating multimodal inputs such as speech, and enhancing system adaptability through continuous learning mechanisms. |
|---|---|
| AbstractList | Gesture recognition has emerged as a pivotal technology for enhancing human-computer interaction (HCI), especially in the context of special education. This study presents a comprehensive gesture recognition and response system that leverages advanced deep learning architectures, including AlexNet, VGG19, ResNet and MobileNet, combined with machine learning algorithms such as support vector machines (SVM) and random forest. The proposed system achieves state-of-the-art performance, with an accuracy of 95.4%, demonstrating its effectiveness in recognising complex gestures with high precision. To address the challenges of deploying gesture recognition systems on resource-constrained devices, the study incorporates genetic algorithms (GAs) for model compression. This optimisation reduces the model size by 42%, significantly enhancing its suitability for real-time applications on mobile and embedded platforms. Additionally, inference time is reduced by 45%, enabling faster response times essential for interactive educational environments. The system was evaluated using a diverse gesture dataset, ensuring robustness across varying lighting conditions, user demographics, and physical differences. The findings highlight the potential of integrating gesture recognition systems into special education, where they can serve as assistive tools for individuals with disabilities, fostering inclusive and engaging learning experiences. This work not only advances the field of gesture recognition but also underscores the importance of model optimisation for real-world applications. Future research will focus on expanding the gesture library, integrating multimodal inputs such as speech, and enhancing system adaptability through continuous learning mechanisms.Gesture recognition has emerged as a pivotal technology for enhancing human-computer interaction (HCI), especially in the context of special education. This study presents a comprehensive gesture recognition and response system that leverages advanced deep learning architectures, including AlexNet, VGG19, ResNet and MobileNet, combined with machine learning algorithms such as support vector machines (SVM) and random forest. The proposed system achieves state-of-the-art performance, with an accuracy of 95.4%, demonstrating its effectiveness in recognising complex gestures with high precision. To address the challenges of deploying gesture recognition systems on resource-constrained devices, the study incorporates genetic algorithms (GAs) for model compression. This optimisation reduces the model size by 42%, significantly enhancing its suitability for real-time applications on mobile and embedded platforms. Additionally, inference time is reduced by 45%, enabling faster response times essential for interactive educational environments. The system was evaluated using a diverse gesture dataset, ensuring robustness across varying lighting conditions, user demographics, and physical differences. The findings highlight the potential of integrating gesture recognition systems into special education, where they can serve as assistive tools for individuals with disabilities, fostering inclusive and engaging learning experiences. This work not only advances the field of gesture recognition but also underscores the importance of model optimisation for real-world applications. Future research will focus on expanding the gesture library, integrating multimodal inputs such as speech, and enhancing system adaptability through continuous learning mechanisms. Gesture recognition has emerged as a pivotal technology for enhancing human-computer interaction (HCI), especially in the context of special education. This study presents a comprehensive gesture recognition and response system that leverages advanced deep learning architectures, including AlexNet, VGG19, ResNet and MobileNet, combined with machine learning algorithms such as support vector machines (SVM) and random forest. The proposed system achieves state-of-the-art performance, with an accuracy of 95.4%, demonstrating its effectiveness in recognising complex gestures with high precision. To address the challenges of deploying gesture recognition systems on resource-constrained devices, the study incorporates genetic algorithms (GAs) for model compression. This optimisation reduces the model size by 42%, significantly enhancing its suitability for real-time applications on mobile and embedded platforms. Additionally, inference time is reduced by 45%, enabling faster response times essential for interactive educational environments. The system was evaluated using a diverse gesture dataset, ensuring robustness across varying lighting conditions, user demographics, and physical differences. The findings highlight the potential of integrating gesture recognition systems into special education, where they can serve as assistive tools for individuals with disabilities, fostering inclusive and engaging learning experiences. This work not only advances the field of gesture recognition but also underscores the importance of model optimisation for real-world applications. Future research will focus on expanding the gesture library, integrating multimodal inputs such as speech, and enhancing system adaptability through continuous learning mechanisms. |
| Author | Xuanfeng, Duan |
| Author_xml | – sequence: 1 givenname: Duan surname: Xuanfeng fullname: Xuanfeng, Duan organization: Graduate School of José Rizal University, Mandaluyong, Manila Province, Philippines |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/40625119$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkE1PwzAMhiM0xD7gJ4B65NKROE2WHtEEA2kSFzhXWepuQW1SmgZpB_47ZWyIi-3Xfl5L9pSMnHdIyDWjc0YVvWOLTHFGF3OgIOYgYAEgz8jkp59yxsToXz0m0xDeKc0kZPyCjDMqQTCWT8jXCkMfO0w6NH7rbG-9S7QrBx1a7wImYR96bJLKd0lo0VhdJ1hGow9kDNZtE-ObNvbYJZ82nPy72GiX_k2sG6I2B1OPZud87bf7S3Je6Trg1THPyNvjw-vyKV2_rJ6X9-u0Bcb7VBgl8gxzgIrJqkTOKlBsQylXfCNRCYlljopiZkSZM0CeVXKjABClELnhM3L7u7ft_EccLi4aGwzWtXboYyg4gKLApKIDenNE46bBsmg72-huX5xexr8BWXZzhA |
| ContentType | Journal Article |
| DBID | NPM 7X8 |
| DOI | 10.1080/17483107.2025.2527226 |
| DatabaseName | PubMed MEDLINE - Academic |
| DatabaseTitle | PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Occupational Therapy & Rehabilitation |
| EISSN | 1748-3115 |
| ExternalDocumentID | 40625119 |
| Genre | Journal Article |
| GroupedDBID | --- 00X 03L 04C 0R~ 29G 36B 4.4 53G 5GY 6PF AAGDL AALUX AAMIU AAPUL AAQRR AAWTL ABBKH ABEIZ ABIVO ABJNI ABLCE ABLIJ ABLKL ABUPF ABWVI ABXYU ACENM ACGFS ACIEZ ACVOX ADBBV ADCVX ADOJX ADRBQ ADYSH AECIN AEOZL AFOSN AFRVT AGDLA AGFJD AGRBW AGYJP AIJEM AIRBT AKBVH ALMA_UNASSIGNED_HOLDINGS ALQZU ALYBC BABNJ BLEHA BMSDO BOHLJ CCCUG CS3 DKSSO EBS ECT F5P H13 HZ~ KSSTO KWAYT KYCEM LJTGL M4Z NPM O9- P2P RNANH RVRKI TASJS TBQAZ TDBHL TERGH TFDNU TFL TFW TUROJ V1S ~1N 7X8 |
| ID | FETCH-LOGICAL-p213t-5c8594e922f16fde31f281b00383b6e856ed9e80e4c5d912e34f6b822ee6559c3 |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001524226100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1748-3115 |
| IngestDate | Fri Sep 05 15:42:44 EDT 2025 Mon Jul 21 06:02:40 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | deep learning model compression MobileNet VGG-19 real-time systems special education Gesture recognition AlexNet assistive technology genetic algorithms machine learning ResNet |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-p213t-5c8594e922f16fde31f281b00383b6e856ed9e80e4c5d912e34f6b822ee6559c3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PMID | 40625119 |
| PQID | 3228021680 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_3228021680 pubmed_primary_40625119 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-07-08 |
| PublicationDateYYYYMMDD | 2025-07-08 |
| PublicationDate_xml | – month: 07 year: 2025 text: 2025-07-08 day: 08 |
| PublicationDecade | 2020 |
| PublicationPlace | England |
| PublicationPlace_xml | – name: England |
| PublicationTitle | Disability and rehabilitation: Assistive technology |
| PublicationTitleAlternate | Disabil Rehabil Assist Technol |
| PublicationYear | 2025 |
| SSID | ssj0046243 |
| Score | 2.3579683 |
| SecondaryResourceType | online_first |
| Snippet | Gesture recognition has emerged as a pivotal technology for enhancing human-computer interaction (HCI), especially in the context of special education. This... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 1 |
| Title | Gesture recognition and response system for special education using computer vision and human-computer interaction technology |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/40625119 https://www.proquest.com/docview/3228021680 |
| WOSCitedRecordID | wos001524226100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAWR databaseName: Taylor & Francis Journals customDbUrl: eissn: 1748-3115 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0046243 issn: 1748-3115 databaseCode: TFW dateStart: 20060101 isFulltext: true titleUrlDefault: https://www.tandfonline.com providerName: Taylor & Francis |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELZoQagXxJvyqIwEXFBK_Ix9RJTCqUJoEXtb5TGWOJCuNgkqB_4740eyWdFKcOASreLEkfx9O54Zz4OQFw2rS1lbkVmnRCZt5TIjbZ3pssINKJesEmVoNlGcnZnl0n5K5Qm60E6gaFtzcWHX_xVqvIdg-9TZf4B7mhRv4G8EHa8IO17_CvgPKOf9qcAUGpTijTcxGhZS8eYQX9jF7vOpfqt_chizcEOvh9cx9Ty8H7r5ZdOIrzOxSY3G-13_fNJ1T1L53v5n-v68JnhwSOL_sQuhS_0fDv7lULYOoiA6GRKFk3eCqxDJGgUqRIlaSO-AZWomJdmlsjsGO_rnUeUsjv1sx1zxgseU-hl06-8BO9RFvIFkt1vZFGA4Du2R67xQ1sf6LU6_jlu01FyKMZ3L5G8u_eYBuTnOcrX1EbSQxW1yK5kP9G2E_Q65Bu1d8nJeKpouYp0I-op-3lnxe-RXogadUYMiNHSkBo3UoEgNmqhBJ2rQQA06EoBGaoT3d6lBZ9SgW2Tvky-n7xfvPmap_Ua25kz0maqNshIs545p14BgjqOR48-SRaXBKA2NBZODrFVjGQchna5Q4QTQaKfW4gHZb89beESoK3WZN6IyrgbZOF5yXjUgpQEIXSEPyfNxgVco3vyZVdnC-dCthC_XxJk2-SF5GFd-tY51WFYjPI-vHHlCDrakfEr2-80Az8iN-kf_rdsckb1iaY4CM34DCL99xQ |
| linkProvider | Taylor & Francis |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Gesture+recognition+and+response+system+for+special+education+using+computer+vision+and+human-computer+interaction+technology&rft.jtitle=Disability+and+rehabilitation%3A+Assistive+technology&rft.au=Xuanfeng%2C+Duan&rft.date=2025-07-08&rft.eissn=1748-3115&rft.spage=1&rft_id=info:doi/10.1080%2F17483107.2025.2527226&rft_id=info%3Apmid%2F40625119&rft.externalDocID=40625119 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1748-3115&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1748-3115&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1748-3115&client=summon |