Automated Quality Assessment of Hand Washing Using Deep Learning

Maksims Ivanovs, Roberts Kadiķis, Atis Elsts, Martins Lulla, Aleksejs Rutkovskis

Research output: Working paperPreprint


Washing hands is one of the most important ways to prevent infectious diseases, including COVID-19. Unfortunately, medical staff does not always follow the World Health Organization (WHO) hand washing guidelines in their everyday work. To this end, we present neural networks for automatically recognizing the different washing movements defined by the WHO. We train the neural network on a part of a large (2000+ videos) real-world labeled dataset with the different washing movements. The preliminary results show that using pre-trained neural network models such as MobileNetV2 and Xception for the task, it is possible to achieve > 64 % accuracy in recognizing the different washing movements. We also describe the collection and the structure of the above open-access dataset created as part of this work. Finally, we describe how the neural network can be used to construct a mobile phone application for automatic quality control and real-time feedback for medical professionals.
Original languageEnglish
Number of pages8
Publication statusPublished - Dec 2020


  • Neural network
  • handwashing
  • handwashing movements

Field of Science*

  • 1.2 Computer and information sciences
  • 2.6 Medical engineering
  • 3.3 Health sciences

Publication Type*

  • 6. Other publications


Dive into the research topics of 'Automated Quality Assessment of Hand Washing Using Deep Learning'. Together they form a unique fingerprint.

Cite this