Shape priors for level set representations
View Patent ↗This invention relates to shape priors for level set representations. An embodiment of the invention comprises a first stage and a second stage. In the first stage, a shape model can be built directly on level set space using a collection of samples. The shape model can be constructed using a variational framework to create a non-stationary pixel-wise model that accounts for shape variabilities. Then, in the second stage, the shape model can be used as basis to introduce the shape prior in an energetic form. In terms of level set representations, the shape prior aims at minimizing non-stationary distance between the evolving interface and the shape model. An embodiment according to the present invention can be integrated with an existing, data-driven variational method to perform image segmentation for physically corrupted and incomplete data.
1. A method for using shape priors for level set representations comprising the steps of:
developing a shape model on level set space for tracking moving interfaces that are used in at least one of a plurality of applications occurring in at least one of a plurality of domains;
using said shape model for introducing a shape prior in an energetic form; and
recovering an object of interest by minimizing non-stationary distance between an evolving interface and said shape model.
2. The method of claim 1 , further comprising the step of integrating said shape model and said shape prior in energetic form into a data-driven variational method that performs image segmentation.
3. The method of claim 1 , wherein developing a shape model includes using a collection of samples.
4. The method of claim 1 , wherein said shape model is developed using a variational framework to create a non-stationary pixel-wise model that accounts for shape variabilities.
5. The method of claim 1 , wherein said at least one of a plurality of applications includes one or more of segmentation, tracking, and reconstruction.
6. The method of claim 1 , wherein said at least one of a plurality of domains includes one or more of medical, surveillance, and automotive.
7. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for using shape priors for level set representations, the method steps comprising:
developing a shape model on level set space for tracking moving interfaces that are used in at least one of a plurality of applications occurring in at least one of a plurality of domains;
using said shape model for introducing a shape prior in an energetic form; and
recovering an object of interest by minimizing non-stationary distance between an evolving interface and said shape model.
8. The program storage device of claim 7 , wherein the method steps further comprise the step of minimizing non-stationary distance between an evolving interface and said shape model.
9. The program storage device of claim 8 , wherein the method steps further comprise the step of integrating said shape model and said shape prior in energetic form into a data-driven variational method that performs image segmentation.
10. The program storage device of claim 7 , wherein the method step of developing a shape model includes using a collection of samples.
11. The program storage device of claim 7 , wherein the shape model is developed using a variational framework to create a non-stationary pixel-wise model that accounts for shape variabilities.
12. The program storage device of claim 7 , wherein said at least one of a plurality of applications includes one or more of segmentation, tracking, and reconstruction.
13. The program storage device of claim 7 , wherein said at least one of a plurality of domains includes one or more of medical, surveillance, and automotive.