Score components (SourceAFIS transparency data)

Detailed scoring, a part of algorithm transparency, is a breakdown of similarity score that is computed by SourceAFIS during matching for a pair of fingerprints. Scoring is done separately for every pairing. Pairing with the highest total score is selected as the best match.

Json

Final similarity score is stored in shapedScore field. Other fields describe intermediate scores that contribute to the final score.

• matchedMinutiae - Number of matched minutiae, regardless of correctness of minutia type or accuracy of angles and distances.
• matchedMinutiaeScore - Scoring for matchedMinutiae.
• matchedFractionOfProbeMinutiae - Fraction of probe minutiae that were successfully paired, including approximate matches like matchedMinutiae.
• matchedFractionOfCandidateMinutiae - Like matchedFractionOfProbeMinutiae but for candidate minutiae.
• matchedFractionOfAllMinutiaeScore - Scoring for matchedFractionOfProbeMinutiae and matchedFractionOfCandidateMinutiae.
• matchedEdges - Number of matched edges, including supporting edges.
• matchedEdgesScore - Scoring for matchedEdges.
• minutiaeWithSeveralEdges - Number of minutiae with at least one supporting edge in addition to edges in the matching tree.
• minutiaeWithSeveralEdgesScore - Scoring for minutiaeWithSeveralEdges.
• correctMinutiaTypeCount - Number of matched minutia pairs where probe and candidate minutia have the same type (ending or bifurcation).
• correctMinutiaTypeScore - Scoring for correctMinutiaTypeCount.
• accurateEdgeLengthScore - Extra score for edges in the pairing tree (excluding support edges) that have very similar edge length.
• accurateMinutiaAngleScore - Extra score for edges in the pairing tree (excluding support edges) that have very similar minutia angles (minutia rotation minus edge rotation). This is calculated separately for reference and neighbor minutiae on every edge.
• totalScore - Total raw score computed by adding together above score components.
• shapedScore - Final similarity score computed from totalScore with the help of monotonic shaping function constructed in such a way as to make shapedScore approximately correspond to FMR (false match rate) thresholds. Increase in shapedScore by 10 points roughly corresponds to 10x lower FMR.

Example: 082-score.json

{
  "matchedMinutiae": 29,
  "matchedMinutiaeScore": 0.928,
  "matchedFractionOfProbeMinutiae": 0.6170212765957447,
  "matchedFractionOfCandidateMinutiae": 0.7435897435897436,
  "matchedFractionOfAllMinutiaeScore": 6.109143480632843,
  "matchedEdges": 299,
  "matchedEdgesScore": 79.235,
  "minutiaeWithSeveralEdges": 29,
  "minutiaeWithSeveralEdgesScore": 5.597,
  "correctMinutiaTypeCount": 26,
  "correctMinutiaTypeScore": 16.354,
  "accurateEdgeLengthScore": 3.0189560439560443,
  "accurateMinutiaAngleScore": 2.79,
  "totalScore": 114.03209952458889,
  "shapedScore": 228.43821506437033
}