An adaptive-focus deformable model using statistical and geometric information

An active contour (snake) model is presented, with emphasis on medical imag ing applications. There are three main novelties in the proposed model. Fir st. an attribute vector is used to characterize the geometric structure aro und each point of the snake model: the deformable model then deforms in a w ay that seeks regions with similar attribute vectors. This is in contrast t o most deformable models, which deform to nearby edges without considering geometric structure. and it was motivated by the need to establish point-co rrespondences that have anatomical meaning. Second, an adaptive-focus stati stical model has been suggested which allows the deformation of the active contour in each stage to be influenced primarily by the most reliable match es. Third, a deformation mechanism that is robust to local minima is propos ed by evaluating the snake energy function on segments of the snake at a ti me, instead of individual points. Various experimental results show the eff ectiveness of the proposed model.