Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
406039 | Neurocomputing | 2015 | 13 Pages |
A novel level set method (LSM) with the constraint of shape priors is proposed to implement a selective image segmentation. Firstly, the shape priors are aligned by using image moment to deprive the spatial related information. Secondly, the aligned shape priors are projected into the subspace expanded by using locality preserving projection to measure the similarity between the shapes. Finally, a new energy functional is built by combing data-driven and shape-driven energy items to implement a selective image segmentation method. We assess the proposed method and some representative LSMs on the synthetic, medical and natural images, the results suggest that the proposed one is superior to the pure data-driven LSMs and the representative LSMs with shape priors.