Please create an account to participate in the Slashdot moderation system

 


Forgot your password?
Close
typodupeerror
×
AI Software Technology

NIST Workshop Explores Automated Tattoo Identification 71

Posted by Soulskill from the database-of-regret dept.
chicksdaddy writes: Security Ledger reports on a recent NIST workshop dedicated to improving the art of automated tattoo identification. It used to be that the only place you'd commonly see tattoos was at your local VA hospital. No more. In the last 30 years, body art has gone mainstream. One in five adults in the U.S. has one. For law enforcement and forensics experts, this is a good thing; tattoos are a great way to identify both perpetrators and their victims. Given the number and variety of tattoos, though, how to describe and catalog them? Clearly this is an area where technology can help, but it's also one of those "fuzzy" problems that challenges the limits of artificial intelligence.

The National Institute of Standards and Technology (NIST) Tattoo Recognition Technology Challenge Workshop challenged industry and academia to work towards developing an automated image-based tattoo matching technology. Participating organizations in the challenge used a FBI -supplied dataset of thousands of images of tattoos from government databases. They were challenged to develop methods for identifying a tattoo in an image, identifying visually similar or related tattoos from different subjects; identifying the same tattoo image from the same subject over time; identifying a small region of interest that is contained in a larger image; and identifying a tattoo from a visually similar image like a sketch or scanned print.
This discussion has been archived. No new comments can be posted.

NIST Workshop Explores Automated Tattoo Identification More

NIST Workshop Explores Automated Tattoo Identification

Comments Filter:

  • Coming to a neck near you ... (Score:3)

    by amalcolm ( 1838434 ) on Monday June 22, 2015 @09:20AM (#49961655)
    Barcodes :)
    • Not that good of a location, hard to see and easy to be covered.
      A better place would be the forehead, would probably be those that are really going with the whole thing. Another good location the top of the hand which is most commonly used by the majority of the population. That way as you reach for stuff you can be verified. Does cause problems for those that don't use that hand so the forehead for them.
      • Not that good of a location, hard to see and easy to be covered.

        Whoosh! That's a reference to the TV show Dark Angel. [wikipedia.org] All of the gene-engineered "soldiers" from Manticore had barcodes on the back of their neck and it wasn't a tattoo, either; if you removed that section of skin, the barcode would still be there when it grew back.

    • No, NIST is working toward a test for the presence of intelligent life in the teenage population.

    • Just put a QR code on your arm that looks like Jesus.

  • This is going to take a lot of testing (Score:5, Funny)

    by Minwee ( 522556 ) <dcr@neverwhen.org> on Monday June 22, 2015 @09:27AM (#49961713) Homepage

    Now, as a competent, dedicated law enforcement professional who is committed to making this project work for the good of society, you're going to need to test it. Thoroughly.

    You need a lot of pictures of people with tattoos, preferably not covered by too much clothing. And you're going to need to double check that the image recognition is correct for every match.

    Once you've done that, you'll need to start applying the same algorithm to video sources. Again, with careful checking to verify that the system is working correctly.

    Where on the Internet are you going to find a huge volume of images and video featuring people with exposed tattoos? And how, exactly, did you just convince the government that it was your job to spend all day watching them while calling it science?

    • Re: (Score:2)

      by jabuzz ( 182671 )

      Depends what you target for identification is. That is if you are looking for something that will give you reasonable grounds to get a search warrant, bring someone in for questioning etc. then it does not need to be perfect.

      • "give you reasonable grounds to get a search warrant"

        Bringing someone in for questioning is one thing. Raiding a private home and ripping the funiture, walls, and floors apart leaving the resident with all financial responsibility and cleanup duty... that should be a MUCH higher bar and should require positive identification to count as reasonable.

    • Re: (Score:3)

      by Nidi62 ( 1525137 )

      Now, as a competent, dedicated law enforcement professional who is committed to making this project work for the good of society, you're going to need to test it. Thoroughly.

      You need a lot of pictures of people with tattoos, preferably not covered by too much clothing. And you're going to need to double check that the image recognition is correct for every match.

      Once you've done that, you'll need to start applying the same algorithm to video sources. Again, with careful checking to verify that the system is working correctly.

      Where on the Internet are you going to find a huge volume of images and video featuring people with exposed tattoos? And how, exactly, did you just convince the government that it was your job to spend all day watching them while calling it science?

      Probably the best way to roll this out would be to target and identify repeat offenders. If you have someone currently incarcerated, you can take good clear pictures of them revealing their tattoos which could then be matched to images of tattoos from crimes committed after they are released/before they were incarcerated.

      MY one concern is this:how good would it be at recognizing altered tattoos or ones that have had additional tattoos added to or applied over the original tattoo? Want to help get away w

      • really? My issue with it would be how do you tell who it's on when there are places tracing and pumping out the same tattoo stencils on thousands of people.

        • >My issue with it would be how do you tell who it's on when there are places tracing and pumping out the same tattoo stencils on thousands of people.

          Some of us can go look at the same tattoo stencil on 100 different people, and tell you which of those people went to the same artist for their tattoo. Given 100 random photographs of the same tattoo stencil, determining which photos are from the same person is trivial.

          • Trivial right up until that common stenciled out tattoo a few thousand people have is the damning evidence at your murder trial in a state you've never been to until they extradited you.

    • Re: (Score:1)

      by Anonymous Coward

      Beyond looking at Suicide Girls...

      See Numerical Recipes, Chapter 16 Classification and Inference (http://www.nr.com/).

      I suspect that the k-means clustering would be a good fit for this. It would probably work well if used on different aspects of the tattoo. For example, there are only so many places where people can generally get tattoos. I have never seen a human with a tattoo on their antennae, for example. You may need to be more specific about some areas than others. For example, "arm" may be too genera

      • > I have never seen a human with a tattoo on their antennae, for example.

        You don't get out much, do you.

        If a needle can be placed on the skin, ink has been placed on that piece of skin.

    • I can send you to a place where there are many uncovered tattoos for testing.

      The local water slide park at Cal Expo in Sacramento.

      I've never seen so many bad tattoos in my life there. It's as if someone gave a 4 year old child a tattoo machine and a line of people a mile long.

      It's quite comical.

  • >> One in five adults in the U.S. has a tattoo

    That seems low in my neighborhood. It seems like most people under 30 have one. It also seems to be a requirement to work in food service or graphic design.

    >> the only place you'd commonly see tattoos was at your local VA hospital

    I don't get this at all. Is this because military men used to be the group that mainly had tattoos? If so, is the author telling us that he/she never knew that many people who served?

    • I don't get this at all. Is this because military men used to be the group that mainly had tattoos?

      Yes, especially Navy enlistees I imagine.

    • >It also seems to be a requirement to work in food service or graphic design.

      In a recent interview with the press, a local pizza owner said that there were some people he hadn't hired, because they had too many tattoos, visible body rings, and the like. The interviewer said that she didn't believe that was possible, given the average number of visible tattoos on the employees of that pizza parlor -- four ear rings, a nose ring, and at least one arm covered with tattoos. The pizza owner responded that it

    • That seems low in my neighborhood. It seems like most people under 30 have one. It also seems to be a requirement to work in food service or graphic design.

      I guess you are a representative sample, and the people charged with acquiring such data are wrong.

      I don't get this at all. Is this because military men used to be the group that mainly had tattoos? If so, is the author telling us that he/she never knew that many people who served?

      Have I ever seen my uncle's tattoos? No, because he covered up his arms b

    • That seems low in my neighborhood. It seems like most people under 30 have one. It also seems to be a requirement to work in food service or graphic design.

      Depends where you live I guess. I'm lucky enough to live in a rich area by a beach, 20% is high here (going to the beach is a giveaway if you have one or not). When I go inland to the working class areas, it seems like every second person has one. The stupid thing about them is that as they are associated with poor and dumb people (have you noticed that in prison the number climbs to nearly 100%), so while getting a tattoo when you're 20 might sound cool at the time, all you are doing is advertising to ever

  • Yes sir! [sonoma.edu]

    And soon a Facebook account will be also required to get a work permit, one room apartment, and exit visa.

    • Just for the record, I gave you the benefit, and no results. You sound like a crazy person, and should stop posting content-free comments on public sites.

      I assume you had a point, but given that you are a crazy person, it must have been as valid as Nick Cage's hair.

  • Not "1 in 5" (Score:2, Insightful)

    by Anonymous Coward

    That was from an survey of 1500 people in the age range of 18 to 25, who are the group most likely to have a tattoo. It in no way reflects on American society as whole.

    It's like polling people in the age range of 80+ about gay marriage, and saying "1 in 5 Americans don't support gay marriage".

    As somebody who crunches numbers all day, trying to pass off results from extremely narrow polls as defining "the face of America" drives me nuts.

    • "As somebody who crunches numbers all day, trying to pass off results from extremely narrow polls as defining "the face of America" drives me nuts."

      Well, consider yourself to have arrived at your destination then!

  • That 1 in 5 is very heavily weighted toward people under 40 and almost everyone under 35 has a tattoo. This should raise the same privacy flags as facial recognition imho and should be illegal everywhere it's illegal to use facial recognition without explicit consent.

  • Most tattoos are terrible, if you put them on paper and framed them you would be embarrassed to hang it in your bathroom.

    I would wager 3 quatloos you could graph the decline of intelligence with the rise of tattoos.

    • eh, it depends. It's an avenue of art, so you could compare it to graffiti or charcoal drawings.
      Sure, there are at least 70% of them that are basically warpaint in another form, 20% that resemble something more than warpaint but are forgettable, then there are the 10% that are basically the persons inner being personified as art outside.

      • Re: (Score:1)

        by koan ( 80826 )

        I've seen some Yakuza tattoos that are OK, but most of the tats I see on the street are just terrible.
        It's amusing how few people understand that symmetry is beautiful.

    • Your point is valid for clothing too.

    • Comment removed based on user account deletion
  • "That person must be smart, he/she has a tattoo."
  • ... does one get an automated tattoo? How is it powered, spilled beer?
  • Many younger people are rebelling against their parents now by not getting tattoos. So many adults have tattoos that it's the norm, and that's "not cool."
    • Tattoos were never a very clever fashion statement. At least with bad jeans or a silly haircut you can change it with the trends. All those idiots will have 2010 printed on them for the rest of their lives. Tattoo removal is going to be a huge business in a few years.

Slashdot Top Deals

Fast, cheap, good: pick two.

Close