Evaluation of AFIS-Ranked Latent Fingerprint Matched Templates

Abstract

Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in:Image and Video Technology: 6th Pacific-Rim Symposium, (PSIVT Abstract. The methodology currently practiced in latent print examination (known as ACE-V) yields only a decision as result, namely individualization, exclusion or inconclusive. From such a decision, it is not possible to express the strength of opinion of a forensic examiner quantitatively with a scientific basis to the criminal justice system. In this paper, we propose a framework to generate a score from the matched template generated by the forensic examiner. Such a score can be viewed as a measure of confidence of a forensic examiner quantitatively, which in turn can be used in statistics-based evidence evaluation framework, for e.g, likelihood ratio. Together with the description and evaluation of new realistic forensic case driven score computation, we also exploit the developed experimental framework to understand more about matched templates in forensic fingerprint databases.

Latent Fingerprint Matching: A Survey

“…Hence, the accuracy of automated latent fingerprint identification is inadequate and also the chances of incorrect identification has increased. Recently, Krish et al [60] extended the current schema of latent fingerprint matching to better enable latent print as an evidence in the court of law. An evaluation on the AFIS ranked matched templates is performed, to statistically quantify the confidence of the examiner for a particular match which can be used in the court of law to highlight the error bounds.…”

Pre‐registration of latent fingerprints based on orientation field

“…NIST‐SD27 [20] is a publicly available forensic fingerprint database which comprises of 258 latent fingerprint images, its matching tenprint images and their minutiae sets. The NIST‐SD27 minutia set database is classified into two [20, 21]: (i) ‘ideal’ and (ii) ‘matched’ minutiae sets. The ‘ideal’ minutiae set for latents was manually extracted by a forensic examiner without any prior knowledge of its corresponding tenprint image.…”

Pre-registration for Improved Latent Fingerprint Identification

“…NIST Special Database 27 (NIST-SD27) [10] is a publicly available forensic fingerprint database which provides minutia sets for latent and its matching tenprint images. The NIST-SD27 minutia set database is broadly classified into two [10] [11]: 1) ideal, and 2) matched minutia set database. The ideal minutia set for latents was manually extracted by a forensic examiner without any prior knowledge of its corresponding tenprint image.…”