A Measurement Metric for Forensic Latent Fingerprint Preprocessing
Haiying Guan, Andrew Dienstfrey, Mary Theofanos, Brian Stanton
Although fingerprint mark-up and identification are well-studied fields, forensic fingerprint image preprocessing is still a relatively new domain in need of further scientific study and development of guidance of best practice. Latent fingerprint image preprocessing is a common step in the forensic analysis workflow that is performed to improve image quality for subsequent identification analysis while simultaneously ensuring data integrity. Due to the low quality of the latent fingerprint images, preprocessing is especially crucial to the success of the final fingerprint identification in the forensic fingerprint image examination. In this report we isolate forensic fingerprint image preprocessing step for more detailed analysis. First we provide a brief review of latent fingerprint image preprocessing. We then turn to the problem of defining image-based quality metric suitable for analysis of forensic latent fingerprint preprocessing. More precisely, we propose to extend Spectral Image Validation and Verification (SIVV)  to serve as a metric for latent fingerprint image quality measurement. SIVV analysis was originally developed to differentiate ten-print or rolled fingerprint images from other non-fingerprint images such as face or iris images. Several modifications are required to extend SIVV analysis to the latent space. We implement, and test this new SIVV-based metric for latent fingerprint image quality and use it to measure the effectiveness of the forensic latent fingerprint preprocessing step. Preliminary results show that the new metric can provide positive indications of both latent fingerprint image quality, and the effectiveness of the fingerprint preprocessing.
, Dienstfrey, A.
, Theofanos, M.
and Stanton, B.
A Measurement Metric for Forensic Latent Fingerprint Preprocessing, NIST Interagency/Internal Report (NISTIR), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.IR.8017
(Accessed December 5, 2023)