Structural Inference Using Deformable Models

Deformable models have proved useful in many machine vision applications during the last decade. To increase performance and to make their use computationally feasible they have to be specifically tuned for the application domain. Model identification and parameter estimation are receiving increasing attention.

The aim of the paper is by no means to give a thorough treatment of the theory behind deformable models, but to illustrate their merits in three practical applications using different types of deformable models: segmenting nano particles, hybridization filter analysis, and shape analysis in the meat industry.

Although not directly developed with remote sensing applications in mind analogous models may be useful in this area.