PDF version of this document
Active appearance models are still not as powerful as active shape models in the sense that they require more time to reach good convergence. Furthermore, the accuracy of appearance models is usually lower19. However, if synthesis of photo-realistic images is a pre-requisite of the model to be used, then AAM's are a unique and exciting technology that does the job adequately.
It is yet hard to ignore the fact that results of an AAM are less accurate than those of an ASM. This brings up the doubts as for whether the extra complexity associated with texture is worthy of being used. The investment of time and intensive effort, including the need for human intervention raises some important issues.
A significant drawback that is associated with appearance models is that automation of model construction, landmark selection [23,24] or more fundamentally image correspondence [25] is somewhat difficult. It is not obvious how to choose landmarks sensibly and how to judge the optimality of an automatic choice of points of significance. Since the efficiency of an appearance model depends greatly on the textures embedded in that model, it is not sufficient to use existing techniques to select landmarks and pseudo-landmarks (additional points between the original anatomical or mathematical landmarks) , as quite recently suggested by Davies et al.[7]. A further explanation of this work is spread throughout the following few sections.