Learning AAM fitting through simulation

The Active Appearance Model (AAM) is a powerful method for modeling and segmenting deformable visual objects. The utility of the AAM stems from two fronts: its compact representation as a linear object class and its rapid fitting procedure, which utilizes fixed linear updates. Although the original fitting procedure works well for objects with restricted variability when initialization is close to the optimum, its efficacy deteriorates in more general settings, with regards to both accuracy and capture range. In this paper, we propose a novel fitting procedure where training is coupled with, and directly addresses, AAM fitting in its deployment. This is achieved by simulating the conditions of real fitting problems and learning the best set of fixed linear mappings, such that performance over these simulations is optimized. The power of the approach does not stem from an update model with larger capacity, but from addressing the whole fitting procedure simultaneously. To motivate the approach, it is compared with a number of existing AAM fitting procedures on two publicly available face databases. It is shown that this method exhibits convergence rates, capture range and convergence accuracy that are significantly better than other linear methods and comparable to a nonlinear method, whilst affording superior computational efficiency.