In the article we present a method for visual face tracking that is based on a wavelet representation of a face tem-plate. The wavelet representation allows arbitrary affine deformations of the facial image, it allows generalizing from an individual face template to a rather general face template and it allows adapting the computational needs of the tracking algorithm to the computational resources available. The method presented was implemented on a Linux Pentium 450 MHz and runs off-line with 25 Hz and on-line, using an active camera mount, with 22 Hz. We present experimental results on off-line tests on several common image sequences including the salesman-sequence as well as on on-line tests.