A multi-class SVM classifier ensemble for automatic hand washing quality assessment
Item Type:Conference Paper
Citation:D.F. Llorca, F. Vilarino, Z. Zhou & G. Lacey, A multi-class SVM classifier ensemble for automatic hand washing quality assessment, British Machine Vision Conference, Warwick, September 2007, 10 pages
Llorca2006.pdf (PDF) 466.5Kb
Hand washing is a critical activity in preventing the spread of infection in health-care environments. Several guidelines recommended a hand washing protocol consisting of six steps that ensure that all areas of the hands are thoroughly cleaned. In this paper, we describe a novel approach that uses a computer vision system to monitor the user’s hands motions in order to ensure that the hand washing guidelines are followed. This work presents two main contributions: a description of a system which delivers robust segmentation of the hands using a combination of colour and motion analysis, and the implementation of a multi-class classification of the hand gestures using a SVM ensemble. The system performance is analysed and compared with human performance, showing an accuracy close to that of human experts.
Other Titles:British Machine Vision Conference
Type of material:Conference Paper
Availability:Full text available