THE FUTURE OF FINGERPRINT EVIDENCE: THE IMPACT OF ARTIFICIAL INTELLIGENCE ON COMPARISON AND ADMISSIBILITY
Loading...
Authors
Perry, Michael T., Jr.
Subjects
fingerprint identification
artificial intelligence
forensic science
image processing
probabilistic modeling
legal admissibility
large language models
Daubert standard
artificial intelligence
forensic science
image processing
probabilistic modeling
legal admissibility
large language models
Daubert standard
Advisors
Peters, Lynda A.
Brown, Shannon A.
Date of Issue
2025-03
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
Fingerprint identification is a cornerstone of forensic science but has been scrutinized for subjectivity and legal reliability. This thesis examines the role of artificial intelligence (AI) in improving fingerprint comparison, enhancing examiner conclusions, and ensuring legal admissibility. By evaluating AI tools, legal precedents, and forensic technology acceptance, the research highlights key advancements. AI-driven image processing can clarify poor-quality prints, machine learning models provide statistical analysis for standardized conclusions, and large language models (LLMs) assist in generating precise, consistent expert reports. LLMs also offer training benefits, integrating statistical reasoning into examiner decision-making and improving courtroom communication. These advancements address longstanding concerns about bias and inconsistency, demonstrating AI’s potential to refine forensic science and legal application. The thesis emphasizes developing scalable frameworks and fostering interdisciplinary collaboration to integrate AI responsibly while meeting evidentiary standards. This thesis ultimately argues that responsible AI integration can modernize fingerprint identification science while reinforcing its reliability in forensic investigations and legal proceedings.
Type
Thesis
Description
Series/Report No
Department
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Distribution Statement A. Approved for public release: Distribution is unlimited.
Rights
Copyright is reserved by the copyright owner.