Image feature matching using polynomial representation of chain codes

Abstract

In this thesis the development of a novel descriptor for boundary images represented in a chain code format is reported. This descriptor is based on a truncated series of orthogonal polynomials used to represent a piecewise continuous function derived from a chain code. This piecewise continuous function is generated from a chain code by mapping individual chain links onto real numbers. A variety of alternative mappings of chain links onto real numbers are evaluated, along with two specific orthogonal polynomials; namely Legendre polynomials and Chebychev polynomials.
The performance of this series descriptor for chain codes is evaluated initially by applying it to the problem of locating short chains within a long chain; and then extending the application and critically evaluating the descriptor when attempting to match features from pairs of similar images.
In addition, a formal algebra is developed that provides the rule base that enables the transformation and manipulation of chain encoded boundary images. The foundation of this algebra is based on the notion that the labelling of the directions of an 8-connected chain code is essentially arbitrary and 7 other, different and consistent labellings can be distinguished.