Thispaperdescribesatechniqueforbuildingcompactmodelsoftheshapeandappearance offlexibleobjects(suchasorgans)seenin2-Dimages. Themodelsarederivedfromthestatisticsof setsof labelled images of examples of the objects. Each model consists of a flexible shape template, describing how important points of the object can vary, and a statistical model of the expected grey levels in regions around each model point. The shape models are parameterised in such a way as to allow `legal' configurations. Such models have proved useful in a wide variety of applications. We describehow the models can be used in local image search and give examples of their application to medicalimages. Wealsodescribehowthemethodcanbesimplyextendedtosegment3-Dobjectsin volumeimages and to track structures in image sequences.
Timothy F. Cootes, Andrew Hill, Christopher J. Tay