418 – Current Research and Evaluation Topics in the American Community Survey
Problems in Approximating and Estimating Mean Shapes of Planar Contours
Leif Ellingson
Texas Tech University
Chalani Prematilake
Texas Tech University
This talk is concerned with problems involved in the similarity shape analysis of planar contours. Contours in this context may be thought of as the ranges of simple closed curves. While contours are by their very nature infinite-dimensional, in order for computations to be performed with digital images, discretization is unavoidable and results in some amount of approximation error. A number of automatic discretization and registration methods are presented to explore the relationship between dimensionality and approximation error. To do so, these methods are applied to estimation of mean shape and classification.