An Approach using Skeleton-based Representations and Neural Networks for Yoga Pose Recognition

Amid a rapidly developing era, people can inevitably have problems with stress, depression, pressure, or difficulty sleeping due to frequent overthinking. To overcome the above problems, yoga will be an excellent solution to help adjust thoughts and harmonize body and soul, helping us relax, relax t...

Full description

Saved in:
Bibliographic Details
Main Authors: Nguyen Hai Thanh, Truong Nguyen Nhat, Pham Linh Thuy Thi, Pham Ngoc Huynh
Format: Article
Language:English
Published: Sciendo 2025-01-01
Series:Applied Computer Systems
Subjects:
Online Access:https://doi.org/10.2478/acss-2025-0009
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849320776414527488
author Nguyen Hai Thanh
Truong Nguyen Nhat
Pham Linh Thuy Thi
Pham Ngoc Huynh
author_facet Nguyen Hai Thanh
Truong Nguyen Nhat
Pham Linh Thuy Thi
Pham Ngoc Huynh
author_sort Nguyen Hai Thanh
collection DOAJ
description Amid a rapidly developing era, people can inevitably have problems with stress, depression, pressure, or difficulty sleeping due to frequent overthinking. To overcome the above problems, yoga will be an excellent solution to help adjust thoughts and harmonize body and soul, helping us relax, relax the mind, and retain positive thoughts. Negative and evil auras will be pushed away, and the worldview will improve. Yoga practice has incorrectly caused many unwanted injuries for practitioners. Therefore, we present an approach grounded in skeleton-based feature extraction and neural networks to find a solution to the recognition of yoga postures, creating a premise for researching a smart virtual trainer that supports home workouts for users from input image data converted into skeleton data through MoveNet. The classification models were used to train recognition and classification of yoga poses. The models were trained and evaluated on a dataset of 3939 images of 10 yoga poses. Experimental results show that the proposed algorithms are entirely suitable for the classification task when achieving good results on different metrics such as Precision, Recall, F1-score, and Accuracy.
format Article
id doaj-art-d574fe54457d4220bc424f3237a2d413
institution Kabale University
issn 2255-8691
language English
publishDate 2025-01-01
publisher Sciendo
record_format Article
series Applied Computer Systems
spelling doaj-art-d574fe54457d4220bc424f3237a2d4132025-08-20T03:49:59ZengSciendoApplied Computer Systems2255-86912025-01-01301758410.2478/acss-2025-0009An Approach using Skeleton-based Representations and Neural Networks for Yoga Pose RecognitionNguyen Hai Thanh0Truong Nguyen Nhat1Pham Linh Thuy Thi2Pham Ngoc Huynh3College of Information and Communication Technology, Can Tho University, Can Tho, VietnamCollege of Information and Communication Technology, Can Tho University, Can Tho, Vietnam3Faculty of Information Technology, Can Tho University of Technology, Can Tho, Vietnam4FPT University, FPT Polytechnic, Can Tho, VietnamAmid a rapidly developing era, people can inevitably have problems with stress, depression, pressure, or difficulty sleeping due to frequent overthinking. To overcome the above problems, yoga will be an excellent solution to help adjust thoughts and harmonize body and soul, helping us relax, relax the mind, and retain positive thoughts. Negative and evil auras will be pushed away, and the worldview will improve. Yoga practice has incorrectly caused many unwanted injuries for practitioners. Therefore, we present an approach grounded in skeleton-based feature extraction and neural networks to find a solution to the recognition of yoga postures, creating a premise for researching a smart virtual trainer that supports home workouts for users from input image data converted into skeleton data through MoveNet. The classification models were used to train recognition and classification of yoga poses. The models were trained and evaluated on a dataset of 3939 images of 10 yoga poses. Experimental results show that the proposed algorithms are entirely suitable for the classification task when achieving good results on different metrics such as Precision, Recall, F1-score, and Accuracy.https://doi.org/10.2478/acss-2025-0009classificationimage classificationmovenetpose recognitionskeleton dataskeleton-based featureyoga pose
spellingShingle Nguyen Hai Thanh
Truong Nguyen Nhat
Pham Linh Thuy Thi
Pham Ngoc Huynh
An Approach using Skeleton-based Representations and Neural Networks for Yoga Pose Recognition
Applied Computer Systems
classification
image classification
movenet
pose recognition
skeleton data
skeleton-based feature
yoga pose
title An Approach using Skeleton-based Representations and Neural Networks for Yoga Pose Recognition
title_full An Approach using Skeleton-based Representations and Neural Networks for Yoga Pose Recognition
title_fullStr An Approach using Skeleton-based Representations and Neural Networks for Yoga Pose Recognition
title_full_unstemmed An Approach using Skeleton-based Representations and Neural Networks for Yoga Pose Recognition
title_short An Approach using Skeleton-based Representations and Neural Networks for Yoga Pose Recognition
title_sort approach using skeleton based representations and neural networks for yoga pose recognition
topic classification
image classification
movenet
pose recognition
skeleton data
skeleton-based feature
yoga pose
url https://doi.org/10.2478/acss-2025-0009
work_keys_str_mv AT nguyenhaithanh anapproachusingskeletonbasedrepresentationsandneuralnetworksforyogaposerecognition
AT truongnguyennhat anapproachusingskeletonbasedrepresentationsandneuralnetworksforyogaposerecognition
AT phamlinhthuythi anapproachusingskeletonbasedrepresentationsandneuralnetworksforyogaposerecognition
AT phamngochuynh anapproachusingskeletonbasedrepresentationsandneuralnetworksforyogaposerecognition
AT nguyenhaithanh approachusingskeletonbasedrepresentationsandneuralnetworksforyogaposerecognition
AT truongnguyennhat approachusingskeletonbasedrepresentationsandneuralnetworksforyogaposerecognition
AT phamlinhthuythi approachusingskeletonbasedrepresentationsandneuralnetworksforyogaposerecognition
AT phamngochuynh approachusingskeletonbasedrepresentationsandneuralnetworksforyogaposerecognition