Name
Abstract | ||
|---|---|---|
We work towards a system which can assist dactyloscopic examiners in assessing the quality and decision value of a fingerprint image and eventually a fingermark. However when quality assessment tasks of datyloscopic examiners are replaced by automatic quality assessment then we need to ensure that the automatic measurement is in agreement with the examiner opinion. Under the assumption of such agreement, we can predict the examiner opinion. We propose a method for determining the examiner agreement on ordinal scales and show that there is a high level of agreement between examiners assessing the ground truth quality of fingerprints. With ground truth quality information on 749 fingerprints and using 10-fold cross validation we construct models using Support Vector Machines and Proportional Odds Logistic Regression which predicts median examiner quality assessments 35% better than when using the prior class distribution. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/BIOSIG.2015.7314616 | 2015 International Conference of the Biometrics Special Interest Group (BIOSIG) |
Keywords | Field | DocType |
dactyloscopic examiner,fingerprint image quality assessments,decision value,ground truth quality,support vector machines,proportional odds logistic regression | Pattern recognition,Ordinal number,Computer science,Support vector machine,Fingerprint image,Ground truth,Artificial intelligence,Odds,Cross-validation,Logistic regression | Conference |
Citations | PageRank | References |
3 | 0.43 | 4 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Martin Aastrup Olsen | 1 | 70 | 6.66 |
| Martin Böckeler | 2 | 3 | 0.43 |
| Christoph Busch | 3 | 28 | 2.96 |