Extracting geometric models through constraint minimization

Geometric models that represent the features in a greyscale image allow for alternative visualizations of the features. These alternatives can lead to a greater understanding of the extents and interrelationships of the features in the image. We present a technique that extracts the geometric nature of a feature by constraining a known geometric model to conform to the characteristics of the feature. The constraints embody local properties of simple polygons and the nature of the relationship between noise and the features in the image. By minimizing these constraints we are able to deform our initial model to fit the feature.