Many tasks in image processing, e.g. segmentation, surface reconstruction, are naturally expressed as energy minimization problems, in which the free variables are shapes, curves in 2d or surfaces in 3d. This approach is intuitive and the flexible; we can easily incorporate data fidelity, geometric regularization and statistical prior terms. Thus we have developed a Python toolbox implementing a diverse collection of shape energies for image processing, and state-of-the-art shape optimization methods. We have have developed crucial shape analysis algorithms for comparisons and statistical analysis. Our Python toolbox is freely available at: http://scikit-shape.org

This is poster number 65 in Poster Session

Authors:

Gunay Dogan (Theiss Research, NIST)

Keywords:

computer vision, image segmentation, image segmentation, shape analysis, shape optimization