Modelling of facial features and its applications

It has been demonstrated by linear regression that contrary to current thinking the relationship between the mouth width and lower lip depth is one of negative association. Early results indicate a strong case for a linear model. Random generation of mouth templates from this model show a good fit to typical image data. An application has been presented which is able to locate and model the lower lip and decide whether a mouth image is open or closed. The parameters of the model are used to classify the located mouth shape into one of a predetermined set. Thus this subsystem/component can be incorporated into existing lip sync systems, where given both streams of data and the knowledge gained from the above system, it would be possible to obtain a better match between the speech and image data in multi-dimensional vector space