The palm vein graph for biometric authentication

We introduce the Palm Vein Graph, a spatial graph representation of the palm vasculature, for use as biometric identifiers. The palm vein image captured from an infra red camera undergoes several image processing steps to be represented as a graph. After image enhancement and binarisation, the palm vein features are extracted from the skeleton using a novel two stage spur removal technique. The location of the features and the connections between them are used to define a Palm Vein Graph. Palm vein graphs are compared using the Biometric Graph Matching (BGM) Algorithm. We propose a graph registration algorithm that incorporates the length of the edges between graph vertices to improve the registration process. We introduce a technique called Graph Trimming that shrinks the compared graphs to achieve faster graph matching and improved performance.We introduce 10 graph topology-based measures for comparing palm vein graphs. Experiments are conducted on a public palm vein database for full and trimmed graphs. For the full graphs, one of the introduced measures, an edgebased similarity, gives a definite improvement in matching accuracies over other published results on the same database. Trimming graphs improves matching performance markedly, especially when the compared graphs had only a small common overlap area due to displacement. For the full graphs, when the edge-based measure was combined with one of three other topological features, we demonstrate an improvement in matching accuracy.