On Latent Fingerprint Image Quality

Abstract

Latent fingerprints which are lifted from surfaces of objects at crime scenes play a very important role in identifying suspects in the crime scene investigations. Due to poor quality of latent fingerprints, automatic processing of latents can be extremely challenging. For this reason, latent examiners need to be involved in latent identification. To expedite the latent identification and alleviate subjectivity and inconsistency in latent examiners’ feature markups and decisions, there is a need to develop latent fingerprint identification systems that can operate in the “lights-out” mode. One of the most important steps in “lights-out” systems is to determine the quality of a given latent to predict the probability that the latent can be identified in a fully automatic manner. In this paper, we (i) propose a definition of latent value determination as a way of establishing the quality of latents based on a specific matcher’s identification performance, (ii) define a set of features based on ridge clarity and minutiae and evaluate them based on their capability to determine if a latent is of value for individualization or not, and (iii) propose a latent fingerprint image quality (LFIQ) that can be useful to reject the latents which cannot be successfully identified in the “lights-out” mode. Experimental results show that the most salient latent features include the average ridge clarity and the number of minutiae. The proposed latent quality measure improves the rank-100 identification rate from 69 % to 86 % by rejecting 50 % of latents deemed as poor quality. In addition, the rank-100 identification is 80 % when rejecting 80 % of the latents in the databases assessed as ‘NFIQ = 5’; however, the same identification rate can be achieved by rejecting only 21 % of the latents with low LFIQ.