Segmenting multiple familiar objects under mutual occlusion

We address the problem of segmenting multiple similar objects by optimizing a Chan-Vese-like [1] functional with respect to a mixture of level set functions. We solve the variational formulation under this model allowing for similarity transforms. This allows shape priors to be enforced even in the presence of mutual occlusion, lifting the limitation in [2]. We show numerical results on example images to demonstrate the promise of our approach. Index Terms — image segmentation, variational methods, shape priors, level set methods, mutual occlusion 1