A Review of Fingerprint Feature Representations and Their Applications for Latent Fingerprint Identification: Trends and Evaluation Article Swipe
YOU?
·
· 2019
· Open Access
·
· DOI: https://doi.org/10.1109/access.2019.2909497
· OA: W2932475397
Latent fingerprint identification is attracting increasing interest because of its important role \nin law enforcement. Although the use of various fingerprint features might be required for successful latent \nfingerprint identification, methods based on minutiae are often readily applicable and commonly outperform \nother methods. However, as many fingerprint feature representations exist, we sought to determine if the \nselection of feature representation has an impact on the performance of automated fingerprint identification \nsystems. In this paper, we review the most prominent fingerprint feature representations reported in the \nliterature, identify trends in fingerprint feature representation, and observe that representations designed for \nverification are commonly used in latent fingerprint identification. We aim to evaluate the performance of \nthe most popular fingerprint feature representations over a common latent fingerprint database. Therefore, \nwe introduce and apply a protocol that evaluates minutia descriptors for latent fingerprint identification \nin terms of the identification rate plotted in the cumulative match characteristic (CMC) curve. From our \nexperiments, we found that all the evaluated minutia descriptors obtained identification rates lower than \n10% for Rank-1 and 24% for Rank-100 comparing the minutiae in the database NIST SD27, illustrating \nthe need of new minutia descriptors for latent fingerprint identification.
