We present a new class of deformable models, MetaMorphs, that consist of both shape and interior texture. The model deformations are derived from both boundary and region information in a common variational framework. This framework represents a generalization of previous model-based segmentation approaches. The shapes of the new models are represented implicitly as "images" in the higher dimensional space of distance transforms. The interior textures are captured using a nonparametric kernel-based approximation of the intensity probability density functions (p.d.f.s) inside the models. The deformations that MetaMorph models can undergo are defined using a space warping technique - the cubic B-spline based Free Form Deformations (FFD). When using the models for boundary finding in images, we derive the model dynamics from an energy functional consisting of both edge energy terms and intensity/texture energy terms. This way, the models deform wider the influence of forces derived from both boundary and regional information. The proposed MetaMorph deformable models are efficient in convergence, have large attraction range, and are robust to image noise and inhomogeities. Various examples on finding object boundaries in noisy images with complex textures demonstrate the potential of the proposed technique.
MetaMorphs: Deformable shape and texture models
2004-01-01
2405706 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
MetaMorphs: Deformable Shape and Texture Models
British Library Conference Proceedings | 2004
|Deformable spatio-temporal shape models: extending active shape models to 2D+time
British Library Online Contents | 2004
|Inverse Shape Design of Deformable Structures and Deformable Wings
Online Contents | 2011
|British Library Conference Proceedings | 1994
|Dynamic 3D Shape from Multi-Viewpoint Images using Deformable Mesh Models
British Library Conference Proceedings | 2003
|