Home Research Teaching Personal

  Main   Mathematical Models in Computer Vision: The Handbook, Springer (2005)

  • Curve Propagation, Level Set Methods and Grouping, N. Paragios
ABSTRACT: Image segmentation and object extraction are among the most well addressed topics in computational vision. In this chapter we propose a comprehensive review of level set-based methods towards a flexible frame partition paradigm that could integrate edge-driven, regional-based and prior knowledge to object extraction. To this end, we explore the use of curve propagation techniques address such a task. The central idea behind such an approach is perform image partition through planar curves/surfaces. To this end, a class of objective functions that aim to account for the expected visual properties of the object as well as to impose certain smoothness constraints is proposed. Furthermore, additional terms are introduced to encode prior knowledge on the geometric form of the object to be recovered.

Last Update: December20th, 2004, you can mail your comments to: nikos.paragios@computer.org