VECTOR FIELD ANALYSIS FOR ORIENTED PATTERNS

We present a method, based on the properties of vector fields, for the estimation of a set of symbolic descriptors (node, saddle, star-node, improper-node, center, and spiral) from linear orientation fields. Pl anar first-order phase portraits are used to model the linear orientat ion fields. A weighted linear estimator is developed to estimate linea r phase portraits, using only the flow orientation. A classification s cheme for planar first-order phase portraits, based on their local pro perties: curl, divergence, and deformation is developed. We present re sults of experiments on noise-added synthetic flow patterns and real o riented textures.