An Improved Ant Colony Matching by Using Discrete Curve Evolution

摘要

In this paper we present an improved Ant Colony Optimization (ACO) for contour matching, which can be used to match 2D shapes. Discrete Curve Evolution (DCE) technique is used to simplify the extracted contour. In order to find the best correspondence between shapes, the match process is formulated as a Quadratic Assignment Problem (QAP) and resolved by using Ant Colony Optimization (ACO). The experimental results justify that Discrete Curve Evolution (DCE) performs better than the previous Constant Sampling (CS) technique which has been selected for the ACO matching.