In this paper we utilise magnetoresitive sensors
and particle filtering to develop a finger tracking system for
physical therapy and human-machine interaction. The aim
of this finger tracking system is to provide a light weight
apparatus with a prolonged operational period. This will
increase its suitability in physical rehabilitation fields where
weight is a premium. The finger tracking algorithm utilises twodimensional
measurements of each joint relative to a magnetic
field reference point to obtain a highly accurate model of
the finger trajectory as opposed to other light weight systems
that can provide only one degree of information. The nonlinear
interaction between joint movements and sensor readings
requires a non-linear filtering technique, as such a particle filter
is utilised to improve the accuracy of the system