Real-world stress testing has become critical before deploying AI systems in law enforcement. Stress testing against actual casework scenarios helps determine system limits and emulate actual error rates with degraded prints, mixed substrates, distorted images, and curved surfaces.
AI has been optimised in law investigations however Angelic Rountree, who is Unit Manager at the D.C. Department of Forensic Sciences, explains the difficult problems that persist when working with biometrics. For example, it becomes difficult to differentiate close non-matches to mitigate false-identification errors. Matching a print against older database enrolments is also tricky given how skin naturally degrades over time. Deep learning tools in Automated Fingerprint Identification Systems have significantly improved match probability by stabilising ridge flows and sifting through background noise.
According to Rountree, AI and biometric technology will improve efficiency, act as a triage layer, and speed up casework processing, with increased integration of statistical models. However, human examiners will remain essential for the final call due to the complex environmental variables involved in how latent prints are deposited.
Hear conversations on AI and forensic biometrics at Identity Week Europe in 2027.
