IEA 2003, International Ergonomics Association XVth Triennial Congress, August 24-29, 2003, Seoul, Korea
Whereas much of the previous work on anthropometric data mining has focused on mining measurements and statistical data, in this paper content-based anthropometric data mining of threedimensional scanned human bodies is discussed. A short review of digitalisation of human bodies is presented. Then it is shown how it is possible to describe the three-dimensional shape of the bodies by representing them with compact support feature vectors. A recurrent data mining system based on these vectors is then presented. This system allows to clustorize the population by using the 'query by example' paradigm and the knowledge of the expert in a recurrent approach. A virtual environment is then used in order to perform visual data mining on the clusters and to characterize the population by defining archetypes. The subject is covered both from the theoretical and implementation point of view. We discuss calculation of the feature vectors, recurrent query by example clustorization, database, virtual environments and definition of the archetypes.
IEA 2003, International Ergonomics Association XVth Triennial Congress [Proceedings].