A User-Centered Framework for Adaptive Fingerprint Identification

Abstract

In recent years, law enforcement personnel have been greatly aided by the deployment of automated fingerprint identification systems (AFIS). These black-box systems largely operate by matching distinctive features automatically extracted from fingerprint images for their decisions. However, current systems have two major shortcomings. First, the identification result depends solely on the chosen features and the algorithm that matches them. Second, these systems cannot improve their results by benefiting from interactions with expert examiners who often can identify small differences between fingerprints. In this paper, we demonstrate by incorporating Relevance Feedback in a fingerprint identification system as an add-on module, a persistent semantic space over the database of fingerprints for an expert user can be incrementally learned. Here, the learning module makes use of a Dimensionality Reduction process that returns both a low-dimensional semantic space and an out-of-sample mapping function, achieving a two-fold benefits of data compression and the ability to project novel fingerprints directly onto the semantic space for identification. Experimental results demonstrated the potential of this user-centered framework for adaptive fingerprint identification.