No Cover Image

Journal article 248 views

Smart Home Control Using Real-Time Hand Gesture Recognition and Artificial Intelligence on Raspberry Pi 5

Thomas Hobbs, Anwar Ali Orcid Logo

Electronics, Volume: 14, Issue: 20, Start page: 3976

Swansea University Authors: Thomas Hobbs, Anwar Ali Orcid Logo

  • 70718.pdf

    PDF | Version of Record

    © 2025 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.

    Download (7.81MB)

Check full text

DOI (Published version): 10.3390/electronics14203976

Abstract

This paper outlines the process of developing a low-cost system for home appliance control via real-time hand gesture classification using Computer Vision and a custom lightweight machine learning model. This system strives to enable those with speech or hearing disabilities to interface with smart...

Full description

Published in: Electronics
ISSN: 2079-9292
Published: MDPI AG 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa70718
first_indexed 2025-10-18T08:36:56Z
last_indexed 2025-12-05T18:10:22Z
id cronfa70718
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-12-04T10:23:52.1532198</datestamp><bib-version>v2</bib-version><id>70718</id><entry>2025-10-18</entry><title>Smart Home Control Using Real-Time Hand Gesture Recognition and Artificial Intelligence on Raspberry Pi 5</title><swanseaauthors><author><sid>2433005846a71867a5aa3363b95314f4</sid><firstname>Thomas</firstname><surname>Hobbs</surname><name>Thomas Hobbs</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>f206105e1de57bebba0fd04fe9870779</sid><ORCID>0000-0001-7366-9002</ORCID><firstname>Anwar</firstname><surname>Ali</surname><name>Anwar Ali</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-10-18</date><deptcode>ACEM</deptcode><abstract>This paper outlines the process of developing a low-cost system for home appliance control via real-time hand gesture classification using Computer Vision and a custom lightweight machine learning model. This system strives to enable those with speech or hearing disabilities to interface with smart home devices in real time using hand gestures, such as is possible with voice-activated &#x2018;smart assistants&#x2019; currently available. The system runs on a Raspberry Pi 5 to enable future IoT integration and reduce costs. The system also uses the official camera module v2 and 7-inch touchscreen. Frame preprocessing uses MediaPipe to assign hand coordinates, and NumPy tools to normalise them. A machine learning model then predicts the gesture. The model, a feed-forward network consisting of five fully connected layers, was built using Keras 3 and compiled with TensorFlow Lite. Training data utilised the HaGRIDv2 dataset, modified to consist of 15 one-handed gestures from its original of 23 one- and two-handed gestures. When used to train the model, validation metrics of 0.90 accuracy and 0.31 loss were returned. The system can control both analogue and digital hardware via GPIO pins and, when recognising a gesture, averages 20.4 frames per second with no observable delay.</abstract><type>Journal Article</type><journal>Electronics</journal><volume>14</volume><journalNumber>20</journalNumber><paginationStart>3976</paginationStart><paginationEnd/><publisher>MDPI AG</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2079-9292</issnElectronic><keywords>machine learning; Computer Vision; gesture recognition; accessibility; smart home control; landmark normalisation; TensorFlow Lite; OpenCV</keywords><publishedDay>10</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-10-10</publishedDate><doi>10.3390/electronics14203976</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace, Civil, Electrical, and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm>Other</apcterm><funders>This research received no external funding.</funders><projectreference/><lastEdited>2025-12-04T10:23:52.1532198</lastEdited><Created>2025-10-18T09:34:22.3094189</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering</level></path><authors><author><firstname>Thomas</firstname><surname>Hobbs</surname><order>1</order></author><author><firstname>Anwar</firstname><surname>Ali</surname><orcid>0000-0001-7366-9002</orcid><order>2</order></author></authors><documents><document><filename>70718__35384__32db0305c6e14461935eea6b6e80606d.pdf</filename><originalFilename>70718.pdf</originalFilename><uploaded>2025-10-18T09:36:49.5699900</uploaded><type>Output</type><contentLength>8186681</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2025 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2025-12-04T10:23:52.1532198 v2 70718 2025-10-18 Smart Home Control Using Real-Time Hand Gesture Recognition and Artificial Intelligence on Raspberry Pi 5 2433005846a71867a5aa3363b95314f4 Thomas Hobbs Thomas Hobbs true false f206105e1de57bebba0fd04fe9870779 0000-0001-7366-9002 Anwar Ali Anwar Ali true false 2025-10-18 ACEM This paper outlines the process of developing a low-cost system for home appliance control via real-time hand gesture classification using Computer Vision and a custom lightweight machine learning model. This system strives to enable those with speech or hearing disabilities to interface with smart home devices in real time using hand gestures, such as is possible with voice-activated ‘smart assistants’ currently available. The system runs on a Raspberry Pi 5 to enable future IoT integration and reduce costs. The system also uses the official camera module v2 and 7-inch touchscreen. Frame preprocessing uses MediaPipe to assign hand coordinates, and NumPy tools to normalise them. A machine learning model then predicts the gesture. The model, a feed-forward network consisting of five fully connected layers, was built using Keras 3 and compiled with TensorFlow Lite. Training data utilised the HaGRIDv2 dataset, modified to consist of 15 one-handed gestures from its original of 23 one- and two-handed gestures. When used to train the model, validation metrics of 0.90 accuracy and 0.31 loss were returned. The system can control both analogue and digital hardware via GPIO pins and, when recognising a gesture, averages 20.4 frames per second with no observable delay. Journal Article Electronics 14 20 3976 MDPI AG 2079-9292 machine learning; Computer Vision; gesture recognition; accessibility; smart home control; landmark normalisation; TensorFlow Lite; OpenCV 10 10 2025 2025-10-10 10.3390/electronics14203976 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University Other This research received no external funding. 2025-12-04T10:23:52.1532198 2025-10-18T09:34:22.3094189 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering Thomas Hobbs 1 Anwar Ali 0000-0001-7366-9002 2 70718__35384__32db0305c6e14461935eea6b6e80606d.pdf 70718.pdf 2025-10-18T09:36:49.5699900 Output 8186681 application/pdf Version of Record true © 2025 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. true eng https://creativecommons.org/licenses/by/4.0/
title Smart Home Control Using Real-Time Hand Gesture Recognition and Artificial Intelligence on Raspberry Pi 5
spellingShingle Smart Home Control Using Real-Time Hand Gesture Recognition and Artificial Intelligence on Raspberry Pi 5
Thomas Hobbs
Anwar Ali
title_short Smart Home Control Using Real-Time Hand Gesture Recognition and Artificial Intelligence on Raspberry Pi 5
title_full Smart Home Control Using Real-Time Hand Gesture Recognition and Artificial Intelligence on Raspberry Pi 5
title_fullStr Smart Home Control Using Real-Time Hand Gesture Recognition and Artificial Intelligence on Raspberry Pi 5
title_full_unstemmed Smart Home Control Using Real-Time Hand Gesture Recognition and Artificial Intelligence on Raspberry Pi 5
title_sort Smart Home Control Using Real-Time Hand Gesture Recognition and Artificial Intelligence on Raspberry Pi 5
author_id_str_mv 2433005846a71867a5aa3363b95314f4
f206105e1de57bebba0fd04fe9870779
author_id_fullname_str_mv 2433005846a71867a5aa3363b95314f4_***_Thomas Hobbs
f206105e1de57bebba0fd04fe9870779_***_Anwar Ali
author Thomas Hobbs
Anwar Ali
author2 Thomas Hobbs
Anwar Ali
format Journal article
container_title Electronics
container_volume 14
container_issue 20
container_start_page 3976
publishDate 2025
institution Swansea University
issn 2079-9292
doi_str_mv 10.3390/electronics14203976
publisher MDPI AG
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering
document_store_str 1
active_str 0
description This paper outlines the process of developing a low-cost system for home appliance control via real-time hand gesture classification using Computer Vision and a custom lightweight machine learning model. This system strives to enable those with speech or hearing disabilities to interface with smart home devices in real time using hand gestures, such as is possible with voice-activated ‘smart assistants’ currently available. The system runs on a Raspberry Pi 5 to enable future IoT integration and reduce costs. The system also uses the official camera module v2 and 7-inch touchscreen. Frame preprocessing uses MediaPipe to assign hand coordinates, and NumPy tools to normalise them. A machine learning model then predicts the gesture. The model, a feed-forward network consisting of five fully connected layers, was built using Keras 3 and compiled with TensorFlow Lite. Training data utilised the HaGRIDv2 dataset, modified to consist of 15 one-handed gestures from its original of 23 one- and two-handed gestures. When used to train the model, validation metrics of 0.90 accuracy and 0.31 loss were returned. The system can control both analogue and digital hardware via GPIO pins and, when recognising a gesture, averages 20.4 frames per second with no observable delay.
published_date 2025-10-10T18:10:22Z
_version_ 1850692833205288960
score 11.08899

Similar Items