Predicting Dactyloscopic Examiner Fingerprint Image Quality Assessments

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 Re- gression which predicts median examiner quality assessments 35\% better than when using the prior class distribution.