Contrary to many other deformable models Active Shape Models (ASM) represents a general way of performing non-rigid object segmentation. Shape variation is extracted from a training set by applying principal component analysis to point distribution models, rather than hand crafting a priori knowledge into the model.
In this paper we investigate different properties of ASM. Topics treated are the generation of plausible shapes, tangent space transformation and model to image fitting assisted by statistical models of gray level variation in the training set. Finally a method for automatic initialization and a comparison of four model to image fitting methods are presented. The initialization part indicates that completely automatic segmentation could be done by ASMs. The comparison part shows an improved fit for model to image fit methods based on gray level variation in the training set.
Deformable Models, Active Shape Models, Snakes, Principal Component Analysis, Statistical Models of Gray Level Variation, Model Initialization.