• lemming@sh.itjust.works
        link
        fedilink
        arrow-up
        21
        ·
        10 months ago

        Have you read the link? It doesn’t say thay that analysing figerprints is less powerfull than was known, but more. It describes previously unknown connection between fingerprints of different fingers of a single person. This could indicate, for example, that two crimes were probably commited by the same person even when not a single identical fingerprint was found on both sites.

        • xthexder@l.sw0.com
          link
          fedilink
          arrow-up
          1
          arrow-down
          2
          ·
          10 months ago

          Seems like pretty flimsy evidence if all we have to go off of is an AI that only gets it right 80% of the time… I highly doubt you could show the 2 fingerprints to anyone else to verify visually, and we’re just supposed to trust it?

          • lemming@sh.itjust.works
            link
            fedilink
            arrow-up
            6
            ·
            10 months ago

            Well, it wouldn’t be good evidence on its own at court, but can very well nudge an investigation in a right direction. And anyway, it’s a first step, done with little resources and ablimited dataset for training. And at least for me, it’sbthe first time I hear something like this is possible at all. Others said that tools to the same effect were around for quite a while, but I haven’t seen anyone providing sources, especially some that would give quantification of its capabilites.