The palm vein graph for biometric authentication

Arathi Arakala, Hao Hao, Stephen Davis, Kathy J. Horadam

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)


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.

Original languageEnglish
Title of host publicationInformation Systems Security and Privacy
Subtitle of host publicationFirst International Conference, ICISSP 2015
EditorsOlivier Camp, Edgar Weippl, Christophe Bidan, Esma Aïmeur
Place of PublicationSwitzerland
PublisherSpringer-Verlag London Ltd.
Number of pages20
ISBN (Electronic)9783319276687
ISBN (Print)9783319276670
Publication statusPublished - 2015
Externally publishedYes
EventInternational Conference on Information Systems Security and Privacy (ICISSP 2015) - ESEO, Angers Loire Valley, France
Duration: 9 Feb 201511 Feb 2015
Conference number: 1st


ConferenceInternational Conference on Information Systems Security and Privacy (ICISSP 2015)
Abbreviated titleICISSP 2015
CityAngers Loire Valley
OtherICISSP 2015 will be held in conjunction with MODELSWARD 2015
All papers presented at the conference venue will be available at the SCITEPRESS Digital Library
Internet address


  • Authentication
  • Biometric graph
  • Graph matching
  • Palm vein

Cite this