Abstract: A prescreen filtering method and algorithm based upon Attributed Relational Graph (ARG) techniques are employed in a node-by-node matching to individually determine a best alignment of the sets of minutia of a pair of search and file fingerprints. First, the directional components of each and every different pair of minutia from the two sets are compared to ensure that they are within a given angular tolerance, which is selected to allow for a reasonable variation in possible rotational misalignments. After this directional alignment tolerance criteria has been passed, a Distance Matrix (DM) score is generated for each passed [u,v] minutia pair by performing a virtual alignment of the [u,v] minutia pair in location and direction, and then by comparing the distances and relative orientations between each of four pairs of minutia neighbors in each of the four local quadrants, which represents how well each different [u,v] minutia pair match each other.

Abstract: A prescreen filtering method and algorithm based upon Attributed Relational Graph (ARG) techniques are employed in a node-by-node matching to individually determine a best alignment of the sets of minutia of a pair of search and file fingerprints. First, the directional components of each and every different pair of minutia from the two sets are compared to ensure that they are within a given angular tolerance, which is selected to allow for a reasonable variation in possible rotational misalignments. After this directional alignment tolerance criteria has been passed, a Distance Matrix (DM) score is generated for each passed [u,v] minutia pair by performing a virtual alignment of the [u,v] minutia pair in location and direction, and then by comparing the distances and relative orientations between each of four pairs of minutia neighbors in each of the four local quadrants, which represents how well each different [u,v] minutia pair match each other.