Automated identification of Shankha Prakshalana yoga poses with machine learning techniques
Abhishek Sharma, Vaidehi Sharma, Premansh Sharma, Rishikesh Ladha, Yogesh Lamba, Sulabh Bansal · 2025
Read Automated identification of Shankha Prakshalana yoga poses with machine learning techniques by Abhishek Sharma, Vaidehi Sharma, Premansh Sharma, Rishikesh Ladha, Yogesh Lamba, Sulabh Bansal (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12775051.txt.
Description
Abhishek Sharma and co-authors trained computer vision tools in 2025 to spot the poses of a cleansing yoga routine from video. The routine, Shankha Prakshalana, uses a set of moves that teachers normally check by eye. A labeled video set of people doing the routine fed several learning methods.
One classic method, a random forest, named the poses with near-perfect accuracy, beating the other tools tried. The authors built the system to watch form and guide practice in settings from clinics to homes. They present the work as a step in joining old yogic practice with modern sensing. Wider use, they note, could help teachers track many students at once.
Catalog record
| CREATOR | Abhishek Sharma, Vaidehi Sharma, Premansh Sharma, Rishikesh Ladha, Yogesh Lamba, Sulabh Bansal |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |