It turns out they are similar, only weve been comparing finger prints the wrong way!From “Law and Order” to “CSI,” not to mention real life, private investigators have actually used finger prints as the gold standard for linking criminals to a criminal activity. If a perpetrator leaves prints from various fingers in 2 different criminal activity scenes, these scenes are extremely difficult to link, and the trace can go cold.Its a well-accepted fact in the forensics neighborhood that fingerprints of different fingers of the very same person– “intra-person finger prints”– are unique, and therefore unmatchable.Research led by Columbia Engineering undergraduateA team led by Columbia Engineering undergraduate senior Gabe Guo challenged this widely held presumption.” The AI was not utilizing minutiae, which are the branchings and endpoints in fingerprint ridges– the patterns used in standard fingerprint comparison,” said Guo, who began the study as a first-year student at Columbia Engineering in 2021.
By Columbia University School of Engineering and Applied Science January 27, 2024An undergraduate-led team at Columbia Engineering utilized AI to challenge the forensic assumption that fingerprints from different fingers of the very same individual are unmatchable, discovering a brand-new kind of forensic marker. It turns out they are comparable, only weve been comparing fingerprints the wrong way!From “Law and Order” to “CSI,” not to point out genuine life, private investigators have actually used finger prints as the gold requirement for connecting criminals to a criminal offense. If a wrongdoer leaves prints from different fingers in 2 different crime scenes, these scenes are extremely tough to link, and the trace can go cold.Its a well-accepted truth in the forensics neighborhood that fingerprints of various fingers of the exact same person– “intra-person fingerprints”– are distinct, and therefore unmatchable.Research led by Columbia Engineering undergraduateA team led by Columbia Engineering undergraduate senior Gabe Guo challenged this widely held presumption. The anonymous specialist reviewer and editor concluded that “It is well understood that every finger print is distinct,” and therefore it would not be possible to find resemblances even if the fingerprints came from the same person.The team did not give up.” The AI was not utilizing minutiae, which are the branchings and endpoints in finger print ridges– the patterns utilized in standard fingerprint comparison,” stated Guo, who started the study as a first-year student at Columbia Engineering in 2021.
