YoNet: A Neural Network for Yoga Pose Classification

• DOI: 10.1007/s42979-022-01618-8
• Publication Date: 2023-02-08T20:30:23Z
• Authors: Faisal Bin Ashraf; Muhammad Usama Islam; Md Rayhan Kabir; Jasim Uddin
• Keywords: Contextual image classification; Residual neural network

Yoga has become an integral part of human life to maintain a healthy body and mind in recent times. With the growing, fast-paced work from home, it difficult for people invest time gymnasium exercises. Instead, they like do assisted exercises at home where pose recognition techniques play most vital role. Recognition different poses is challenging due proper dataset classification architecture. In this work, we have proposed deep learning-based model identify five yoga comparatively fewer amounts data. We compared our model's performance with some state-of-the-art image models-ResNet, InceptionNet, InceptionResNet, Xception found architecture superior. Our extracts spatial, depth features individually considers them further calculation classification. The experimental results show that achieved 94.91% accuracy 95.61% precision.