Abstract: A method for detecting an object in an image includes determining a shape model from aligned training examples, and implementing the shape model as a prior within a level set framework for determining the object in the image, wherein the level set framework determines a projection of the object in the image and a confidence measure along portions of the projection, the level set framework being constrained by the prior.

Abstract: A method of incorporating user supplied information in level-set based image segmentation includes providing a digital image comprising a plurality of intensities corresponding to a domain of points, providing an embedding function on the image domain, obtaining from a user a control point in the image, selecting two end points from the image, the end points being in a level set of the embedding function, interpolating an interactive segment from the user supplied control point and the two end points, replacing a curve segment in the level set between the two endpoints with the interactive segment to form a shape constraint, and time-evolving the embedding function so as to minimize the difference between the level set of the embedding function and the shape constraint.

Abstract: A method for detecting an object in an image includes determining a shape model from aligned training examples, and implementing the shape model as a prior within a level set framework for determining the object in the image, wherein the level set framework determines a projection of the object in the image and a confidence measure along portions of the projection, the level set framework being constrained by the prior.

Abstract: A method of incorporating user supplied information in level-set based image segmentation includes providing a digital image comprising a plurality of intensities corresponding to a domain of points, providing an embedding function on the image domain, obtaining from a user a control point in the image, selecting two end points from the image, the end points being in a level set of the embedding function, interpolating an interactive segment from the user supplied control point and the two end points, replacing a curve segment in the level set between the two endpoints with the interactive segment to form a shape constraint, and time-evolving the embedding function so as to minimize the difference between the level set of the embedding function and the shape constraint.

Abstract: A boundary extraction system comprises a regularity constraint module for, shrinking a curve towards a boundary of one or more objects, a bi-directional curve module for moving the curve towards the object boundaries, and an adaptive balloon force module.