RESUMO
The process of linking an offender to a crime scene via their fingerprints has historically required significant human effort to compare latent fingerprints recovered from the scene with known fingerprints of a suspect. Increasing the speed of such comparisons, whilst maintaining accuracy and reliability and minimising error, is crucial for providing rapid intelligence to police investigators. One major opportunity for streamlining fingerprint examination is the adaptation of 'lights-out' technology to the comparison and matching of latent fingerprints. Here, we review the development, trial and validation process undertaken by the Queensland Police Service (QPS), Australia, to support implementation of a lights-out latent (LOL) workflow for automated latent fingerprint searching that is fully integrated with the existing case management systems. Targeted trials were undertaken using random selections of previously identified latent fingerprints that were searched using the LOL workflow against a local 10-print database. The results suggested that the LOL workflow could identify up to 44% of latent fingerprints with minimal human intervention and supported its implementation for all latent fingerprint comparisons in QPS casework. Review of LOL casework comparison outcomes for 2019 revealed that LOL-based identifications contributed approximately one quarter of all fingerprint identifications. Several procedural and technical factors that influenced the speed and efficiency of the LOL workflow are discussed, along with opportunities for improvement and future validation as an expert system.