YogiCombineDeep: Enhanced Yogic Posture Classification Using Combined Deep Fusion of VGG16 and VGG19 Features

Yoga garnered significant attention during this pandemic based on its physical benefits in recent years. Regular yoga practice can enhance both physical and mental health. However, some body parts are occluded due to the significant variations in specific asanas with complicated posture formations a...

Full description

Saved in:
Bibliographic Details
Main Authors: Arun Kumar Rajendran, Sibi Chakkaravarthy Sethuraman
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10557613/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850191623330201600
author Arun Kumar Rajendran
Sibi Chakkaravarthy Sethuraman
author_facet Arun Kumar Rajendran
Sibi Chakkaravarthy Sethuraman
author_sort Arun Kumar Rajendran
collection DOAJ
description Yoga garnered significant attention during this pandemic based on its physical benefits in recent years. Regular yoga practice can enhance both physical and mental health. However, some body parts are occluded due to the significant variations in specific asanas with complicated posture formations and their backgrounds, making yogic posture detection more complex. This study establishes the classification of yoga postures in the yoga-16 dataset utilizing the combination of deep learning and machine learning approaches. A pre-trained CNN architecture VGG16 and VGG19 collects the deep features from the images of yoga postures. Then, the collected features are combined and entered into classifiers to train and assess the outcome of yoga posture classification. To classify the yogic postures from the collected yoga-16 dataset, the proposed model includes logistic regression, support vector machines, random forest, and extra tree classifiers. The proposed approach examined the yoga-16 dataset containing 16 classes and 6561 images. The proposed combined deep-fused approach utilizing Linear SVM yields better results than all the existing yogic posture classification models with outstanding scores of 99.94% precision, 99.94% recall, 100% f1-score, and 99.92% accuracy, respectively. The results show that the proposed approach is effective at attaining excellent performance in yogic posture classification. Performance comparisons with the most recent models have also been listed.
format Article
id doaj-art-c26e8fd67dd14b6ca5744d982dcfc391
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c26e8fd67dd14b6ca5744d982dcfc3912025-08-20T02:14:51ZengIEEEIEEE Access2169-35362024-01-011213916513918010.1109/ACCESS.2024.341465410557613YogiCombineDeep: Enhanced Yogic Posture Classification Using Combined Deep Fusion of VGG16 and VGG19 FeaturesArun Kumar Rajendran0https://orcid.org/0000-0002-9669-1752Sibi Chakkaravarthy Sethuraman1https://orcid.org/0000-0002-2808-0482Center of Excellence, Artificial Intelligence and Robotics (AIR), School of Computer Science and Engineering, VIT-AP University, Amaravathi, IndiaCenter of Excellence, Artificial Intelligence and Robotics (AIR), School of Computer Science and Engineering, VIT-AP University, Amaravathi, IndiaYoga garnered significant attention during this pandemic based on its physical benefits in recent years. Regular yoga practice can enhance both physical and mental health. However, some body parts are occluded due to the significant variations in specific asanas with complicated posture formations and their backgrounds, making yogic posture detection more complex. This study establishes the classification of yoga postures in the yoga-16 dataset utilizing the combination of deep learning and machine learning approaches. A pre-trained CNN architecture VGG16 and VGG19 collects the deep features from the images of yoga postures. Then, the collected features are combined and entered into classifiers to train and assess the outcome of yoga posture classification. To classify the yogic postures from the collected yoga-16 dataset, the proposed model includes logistic regression, support vector machines, random forest, and extra tree classifiers. The proposed approach examined the yoga-16 dataset containing 16 classes and 6561 images. The proposed combined deep-fused approach utilizing Linear SVM yields better results than all the existing yogic posture classification models with outstanding scores of 99.94% precision, 99.94% recall, 100% f1-score, and 99.92% accuracy, respectively. The results show that the proposed approach is effective at attaining excellent performance in yogic posture classification. Performance comparisons with the most recent models have also been listed.https://ieeexplore.ieee.org/document/10557613/Yoga pose classificationVGG16VGG19machine learningdeep learning modelscombined features
spellingShingle Arun Kumar Rajendran
Sibi Chakkaravarthy Sethuraman
YogiCombineDeep: Enhanced Yogic Posture Classification Using Combined Deep Fusion of VGG16 and VGG19 Features
IEEE Access
Yoga pose classification
VGG16
VGG19
machine learning
deep learning models
combined features
title YogiCombineDeep: Enhanced Yogic Posture Classification Using Combined Deep Fusion of VGG16 and VGG19 Features
title_full YogiCombineDeep: Enhanced Yogic Posture Classification Using Combined Deep Fusion of VGG16 and VGG19 Features
title_fullStr YogiCombineDeep: Enhanced Yogic Posture Classification Using Combined Deep Fusion of VGG16 and VGG19 Features
title_full_unstemmed YogiCombineDeep: Enhanced Yogic Posture Classification Using Combined Deep Fusion of VGG16 and VGG19 Features
title_short YogiCombineDeep: Enhanced Yogic Posture Classification Using Combined Deep Fusion of VGG16 and VGG19 Features
title_sort yogicombinedeep enhanced yogic posture classification using combined deep fusion of vgg16 and vgg19 features
topic Yoga pose classification
VGG16
VGG19
machine learning
deep learning models
combined features
url https://ieeexplore.ieee.org/document/10557613/
work_keys_str_mv AT arunkumarrajendran yogicombinedeepenhancedyogicpostureclassificationusingcombineddeepfusionofvgg16andvgg19features
AT sibichakkaravarthysethuraman yogicombinedeepenhancedyogicpostureclassificationusingcombineddeepfusionofvgg16andvgg19features