[Sigia-l] "Gait code"

[Listera]

Eric Scheid:

> So if I stub my toe and start limping, or am staggering about drunk, or
> wearing a tight sari, my phone will pester me with password prompts?

Only if you're techno-illiterate.

A lot of the pattern recognition/context analysis software out there are
trained to detect and compensate for deviations from the baseline. For
example, you can shave, grow a beard, get older, put make up on, have
plastic surgery done, change contact lens color, etc., and they'll still
recognize you. They'll couple that with your gait, breathing/voice/speech
pattern, body temperature and other input including reference to stored data
to verify/challenge/link/etc to refine the process. That's heck of lot more
contextual analysis than a human can perform in real-time and in volume.

Since you love these, here's another innovation: We're all now consumed
these days with tagging physical items to track them with holograms, RFID
tags, 2-3D barcode systems, etc. These involve a lot of effort,
standardization and expense. Now comes a British company, Ingenia, to
completely dispense with the notion of physically tagging individual items
by taking advantage of laser speckle.

"Light coming from a focused laser is coherent, or in phase, but when it
strikes a microscopically rough surface like a piece of paper, the light is
scattered, producing a pattern of light and dark 'speckles.' The scanner's
photodetectors digitize and record this pattern."

<http://www.wired.com/news/privacy/0,1848,68352,00.html?tw=rss.TOP>

"This scan serves as a fingerprint which, the scientists said, has two
surprising properties: The fingerprints are robust, surviving scorching,
dousing in water, crumpling, and scribbling over with pens. And these
fingerprints depend on structures that are so complex and so small -- on the
scale of between one tenth and one ten-thousandth the diameter of a human
hair -- that nobody on the planet will be able to copy one for the
foreseeable future. Unlike other methods such as using holograms or special
inks, the fingerprint is already there."

<http://tinyurl.com/e3y84>

Why is this relevant? Because it shows that even our most fundamental
assumptions (to track something we have to physically tag it, for example)
can be rendered obsolete by technical innovation. The one that you seem to
cling to, that machines cannot do contextual analysis, is one of them.

The real question here, of course, is why am I educating you on these
matters without compensation? :-)

---- 
Ziya

Best Practices,
For when you've run out of your own ideas and context.