Automated Determination of Fingerprint Ridge Density and Fingerprint Size to Detect Sex Differences

Abstract

A fingerprint is probably the most important biometric feature when trying to link a suspect to a crime scene. So far, without a hit in a fingerprint database, it was impossible to use a collected fingerprint to narrow down the group of suspects. Moreover, in the existing studies about deriving phenotypic characteristics from fingerprints the analyses were done manually. In contrast, in this paper a procedure is presented to automatically determine the fingerprint ridge density and the fingerprint size, in order to derive information about the sex of the person the fingerprint belongs to. All 10 fingerprints of 140 individuals (70 males and 70 females) belonging to the German Caucasian population were secured and then analyzed. The best result was obtained for the ulnar area in combination with the fingerprint size of the left thumb with F1 measures of 0.84 (k-nearest neighbors algorithm - KNN), 0.833 (Support Vector Machine) and 0.817 (logistic regression).