DEEP LEARNING FOR GESTURE ANALYSIS IN PERFORMANCE TRAINING
DOI:
https://doi.org/10.29121/shodhkosh.v6.i5s.2025.6904Keywords:
Deep Learning, Gesture Analysis, Performance Training, Pose Estimation, Temporal Modeling, Motion Analytics, Intelligent CoachingAbstract [English]
Gesture analysis is an important element in performance training in various areas including dance, sports, theatre, music and rehabilitation, whereby accurate movement of the body, time and expressiveness is important to the overall quality. The method of traditional gesture evaluation is biased on professional observation, and this method is subjective, cumbersome and cannot be scaled. This paper describes a deep learning-based gesture recognition system in the area of performing training to provide objective and data-driven feedback and individualized skills acquisition. The suggested method combines pose estimation with the help of computer vision and the deep neural framework, such as Convolutional Neural Networks (CNNs) to extract spatial features and Long Short-Term Memory (LSTM) or Transformer models to model temporal motion. Multi-dimensional gesture characteristics like joint paths, velocity signals, symmetry, balance and rhythmical consistency are trained directly by video sequences without any physical feature engineering. The framework facilitates real time and offline analysis that enables performers to get corrective feedback in real time or performance longitudinally. Empirical analyses show that deep learning models are far more efficient than the traditional machine learning methods on accuracy of gesture identification, detection of temporal alignment, movement quality evaluation. It is also possible to score expressiveness, coordination and consistency quantitatively with the help of the system, which helps to train and measure progress. The proposed deep learning-based gesture analysis framework should have significant potential in intelligent performance training systems, online coach environments, and simulated learning environments, owing to the subjectivity reduction and increased accessibility.
References
Agab, S. E., and Chelali, F. Z. (2023). New Combined DT-CWT and HOG Descriptor for Static and Dynamic Hand Gesture Recognition. Multimedia Tools and Applications, 82(18), 26379–26409. https://doi.org/10.1007/s11042-023-14433-x DOI: https://doi.org/10.1007/s11042-023-14433-x
Chang, V., Eniola, R. O., Golightly, L., and Xu, Q. A. (2023). An Exploration Into Human-Computer Interaction: Hand Gesture Recognition Management in a Challenging Environment. SN Computer Science, 4(441). https://doi.org/10.1007/s42979-023-01751-y DOI: https://doi.org/10.1007/s42979-023-01751-y
Chen, H., Leu, M. C., and Yin, Z. (2022). Real-Time Multi-Modal Human-Robot Collaboration Using Gestures and Speech. Journal of Manufacturing Science and Engineering, 144(10), 101007. https://doi.org/10.1115/1.4054297 DOI: https://doi.org/10.1115/1.4054297
Dewi, C., Chen, A. P. S., and Christanto, H. J. (2023). Deep Learning for Highly Accurate Hand Recognition Based on Yolov7 Model. Big Data and Cognitive Computing, 7(1), 53. https://doi.org/10.3390/bdcc7010053 DOI: https://doi.org/10.3390/bdcc7010053
Feng, Z., Huang, J., Zhang, W., Wen, S., Liu, Y., and Huang, T. (2025). YOLOv8-G2F: A Portable Gesture Recognition Optimization Algorithm. Neural Networks, 188, 107469. https://doi.org/10.1016/j.neunet.2025.107469 DOI: https://doi.org/10.1016/j.neunet.2025.107469
Hax, D. R. T., Penava, P., Krodel, S., Razova, L., and Buettner, R. (2024). A Novel Hybrid Deep Learning Architecture for Dynamic Hand Gesture Recognition. IEEE Access, 12, 28761–28774. https://doi.org/10.1109/ACCESS.2024.3365274 DOI: https://doi.org/10.1109/ACCESS.2024.3365274
Kang, P., Li, J., Fan, B., Jiang, S., and Shull, P. B. (2022). Wrist-Worn Hand Gesture Recognition While Walking Via Transfer Learning. IEEE Journal of Biomedical and Health Informatics, 26(3), 952–961. https://doi.org/10.1109/JBHI.2021.3100099 DOI: https://doi.org/10.1109/JBHI.2021.3100099
Knights, E., Mansfield, C., Tonin, D., Saada, J., Smith, F. W., and Rossit, S. (2021). Hand-Selective Visual Regions Represent How to Grasp 3D Tools: Brain Decoding During Real Actions. Journal of Neuroscience, 41(24), 5263–5273. https://doi.org/10.1523/JNEUROSCI.0083-21.2021 DOI: https://doi.org/10.1523/JNEUROSCI.0083-21.2021
Miah, A. S. M., Hasan, M. A. M., and Shin, J. (2023). Dynamic Hand Gesture Recognition Using Multi-Branch Attention-Based Graph and General Deep Learning Model. IEEE Access, 11, 4703–4716. https://doi.org/10.1109/ACCESS.2023.3235368 DOI: https://doi.org/10.1109/ACCESS.2023.3235368
Mujahid, A., Awan, M. J., Yasin, A., Mohammed, M. A., Damaševičius, R., Maskeliūnas, R., and Abdulkareem, K. H. (2021). Real-Time Hand Gesture Recognition Based on Deep Learning Yolov3 Model. Applied Sciences, 11(9), 4164. https://doi.org/10.3390/app11094164 DOI: https://doi.org/10.3390/app11094164
Qiang, B., Zhai, Y., Zhou, M., Yang, X., Peng, B., Wang, Y., and Pang, Y. (2021). Squeezenet and Fusion Network-Based Accurate Fast Fully Convolutional Network for Hand Detection and Gesture Recognition. IEEE Access, 9, 77661–77674. https://doi.org/10.1109/ACCESS.2021.3079337 DOI: https://doi.org/10.1109/ACCESS.2021.3079337
Yaseen, Kwon, O.-J., Kim, J., Lee, J., and Ullah, F. (2025). Evaluation of Benchmark Datasets and Deep Learning Models with Pre-Trained Weights for Vision-Based Dynamic Hand Gesture Recognition. Applied Sciences, 15(11), 6045. https://doi.org/10.3390/app15116045 DOI: https://doi.org/10.3390/app15116045
Zhang, G., Su, J., Zhang, S., Qi, J., Hou, Z., and Lin, Q. (2025). Research on Deep Learning-Based Human-Robot Static/Dynamic Gesture-Driven Control Framework. Sensors, 25(23), 7203. https://doi.org/10.3390/s25237203 DOI: https://doi.org/10.3390/s25237203
Zhang, P., and Zhao, B. (2025). Gesture Recognition Achieved by Utilizing Lora Signals and Deep Learning. Sensors, 25(5), 1446. https://doi.org/10.3390/s25051446 DOI: https://doi.org/10.3390/s25051446
Zhang, Z.-Y., Ren, H., Li, H., Yuan, K.-H., and Zhu, C.-F. (2025). Static Gesture Recognition Based on Thermal Imaging Sensors. Journal of Supercomputing, 81(1), 610. https://doi.org/10.1007/s11227-025-07140-x DOI: https://doi.org/10.1007/s11227-025-07140-x
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Dr. Anusha Sreeram, Pratibha Sharma, Ms. Kairavi Mankad, Kalpana Rawat, Rahul Kumar Sharma, Milind Patil
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
