作者: A. Arakala , S. A. Davis , K. J. Horadam
DOI: 10.1109/IJCB.2011.6117506
关键词: Artificial intelligence 、 Strength of a graph 、 Multiple edges 、 Multigraph 、 Combinatorics 、 Complement graph 、 Ordered graph 、 Null graph 、 Pattern recognition 、 Random geometric graph 、 Computer science 、 Butterfly graph
摘要: We represent the retina vessel pattern as a spatial relational graph, and match features using error-correcting graph matching. study distinctiveness of nodes (branching crossing points) compared with that edges other substructures (nodes degree k, paths length k). On training set from VARIA database, we show well nodes, three types sub-structure completely or almost separate genuine imposter comparisons. combining can improve separation distance. identify two statistics, edge-to-node ratio variance distribution, have low correlation node score.