<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=us-ascii"><meta name=Generator content="Microsoft Word 15 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:#954F72;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri",sans-serif;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=EN-US link="#0563C1" vlink="#954F72"><div class=WordSection1><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>OK cool, so now I get to be the local hipster for the first time. <o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>My son plays this new game, PokemonGo and loves it. Yesterday at the local park we saw a couple dozen players and could easily tell what they were doing. This game gets partway there to something I have been anticipating for a long time: some kind of virtual reality in which characters or something is superimposed on the scene to create a VR. <o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>What I am thinking of now is the next step. PokemonGo has feedback in a crude sense: it reacts to where the player is located. But using a cell phone, it looks like we have everything we need to do image-recognition feedback loops.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>An example I have used before to describe this is in repairing the secondary gear case of a Suzuki Cavalcade. Since we know exactly what that gear case looks like, the image recognition task is limited to a workable scale. When a phone is held about a meter from that gearcase, the software would recognize it and point to the four bolts which must be removed to get to the next step. It could tell you the size wrench needed, the torque value on reassembly, etc.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>Have we any image-recognition gurus or semi-hipsters among us who can comment on how difficult is this problem? I am thinking of a very limited, closed-ended image recognition subroutine which would recognize the outline of a known quantity, such as a specific motorcycle part. Software can recognize faces; this seems trivially easy in comparison. It seems like just a scale and rotate problem to get what the camera sees to match what it is looking for.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>spike<o:p></o:p></p></div></body></html>