Modeling the growth of fingerprints improves matching for adolescents

TL;DR

This paper introduces a simple rescaling method based on growth charts to improve fingerprint matching accuracy for adolescents, significantly reducing error rates in large-scale databases.

Contribution

The study demonstrates that modeling fingerprint growth as proportional to stature growth improves matching accuracy and can be easily integrated into existing systems.

Findings

72% reduction in fingerprint distance after rescaling

Error rate decreased from 20.8% to 2.1% in large database

Growth-based rescaling enhances fingerprint identification for juveniles

Abstract

We study the effect of growth on the fingerprints of adolescents, based on which we suggest a simple method to adjust for growth when trying to recover a juvenile's fingerprint in a database years later. Based on longitudinal data sets in juveniles' criminal records, we show that growth essentially leads to an isotropic rescaling, so that we can use the strong correlation between growth in stature and limbs to model the growth of fingerprints proportional to stature growth as documented in growth charts. The proposed rescaling leads to a 72% reduction of the distances between corresponding minutiae for the data set analyzed. These findings were corroborated by several verification tests. In an identification test on a database containing 3.25 million right index fingers at the Federal Criminal Police Office of Germany, the identification error rate of 20.8% was reduced to 2.1% by rescaling. The presented method is of striking simplicity and can easily be integrated into existing automated fingerprint identification systems.