Classifying transformation-variant attributed point patterns

This paper presents a classification approach, where a sample is represented by a set of feature vectors called an attributed point pattern. Some attributes of a point are transformational-variant, such as spatial location, while others convey some descriptive feature, such as intensity. The proposed algorithm determines a distance between point patterns by minimizing a Hausdorff-based distance over a set of transformations using a particle swarm optimization. When multiple training samples are available for each class, we implement multidimensional scaling to represent the point patterns in a low-dimensional Euclidean space for visualization and analysis. Results are demonstrated for latent fingerprints from tenprint data and civilian vehicles from circular synthetic aperture radar imagery.