<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)"><!--[if !mso]><style>v\:* {behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style><![endif]--><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.MsoPlainText, li.MsoPlainText, div.MsoPlainText
{mso-style-priority:99;
mso-style-link:"Plain Text Char";
margin:0in;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
span.PlainTextChar
{mso-style-name:"Plain Text Char";
mso-style-priority:99;
mso-style-link:"Plain Text";
font-family:"Calibri",sans-serif;}
.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" style='word-wrap:break-word'><div class=WordSection1><p class=MsoPlainText><o:p> </o:p></p><p class=MsoPlainText><o:p> </o:p></p><p class=MsoPlainText>-----Original Message-----<br>From: extropy-chat <extropy-chat-bounces@lists.extropy.org> On Behalf Of BillK via extropy-chat<br>Sent: Wednesday, September 8, 2021 10:09 AM<br>To: ExI chat list <extropy-chat@lists.extropy.org><br>Cc: BillK <pharos@gmail.com><br>Subject: Re: [ExI] Google AI low-resolution photo enhancement</p><p class=MsoPlainText><o:p> </o:p></p><p class=MsoPlainText>On Wed, 8 Sept 2021 at 17:14, spike jones via extropy-chat <<a href="mailto:extropy-chat@lists.extropy.org"><span style='color:windowtext;text-decoration:none'>extropy-chat@lists.extropy.org</span></a>> wrote:<o:p></o:p></p><p class=MsoPlainText>><o:p> </o:p></p><p class=MsoPlainText>> Dave I agree with the notion of enhancing photos of perps but not so fast on the license plates. Those are two different things.<o:p></o:p></p><p class=MsoPlainText>><o:p> </o:p></p><p class=MsoPlainText><big snip><o:p></o:p></p><p class=MsoPlainText>><o:p> </o:p></p><p class=MsoPlainText>> spike<o:p></o:p></p><p class=MsoPlainText>> _______________________________________________<o:p></o:p></p><p class=MsoPlainText><o:p> </o:p></p><p class=MsoPlainText><o:p> </o:p></p><p class=MsoPlainText>>… I think you may be underestimating the power of the Google AI There are more detailed descriptions of the process available in links from the article. Sure, if you only have a few pixels available in the original, then there won't be enough data to expand into a photo. But most cameras (Nest, etc.) have much more than a few pixels available.<o:p></o:p></p><p class=MsoPlainText>I think the AI does backward and forwards resolving to check that the final photo does blur back down to the original photo, to check that the expansion is valid.<o:p></o:p></p><p class=MsoPlainText><o:p> </o:p></p><p class=MsoPlainText>But we should see implementations appearing soon, if it lives up to the hype.<o:p></o:p></p><p class=MsoPlainText><o:p> </o:p></p><p class=MsoPlainText><o:p> </o:p></p><p class=MsoPlainText>BillK<o:p></o:p></p><p class=MsoPlainText>_______________________________________________<o:p></o:p></p><p class=MsoPlainText><o:p> </o:p></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p><p class=MsoPlainText><span style='color:black'>BillK, the notion of enhancing images of a person does work if we have a limited subset of possibilities.<o:p></o:p></span></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p><p class=MsoPlainText><span style='color:black'>For instance, imagine a murder where we know the perp is one of these people: Colonel Mustard, Mrs. Peacock, Professor Plum... <o:p></o:p></span></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p><p class=MsoPlainText><span style='color:black'>If you already know it is one of say... 8 suspects, photo enhancement can be done because we know a limited set of endpoints. Without that, our best centroiding extrapolations can still produce nothing more certain than a police artists' sketch which depends on witnesses verbal description. That process kinda works to some extent sometimes. But not always:<o:p></o:p></span></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p><p class=MsoPlainText><img border=0 width=306 height=239 style='width:3.1875in;height:2.4895in' id="Picture_x0020_1" src="cid:image001.jpg@01D7A49D.D8923440"><span style='color:black'><o:p></o:p></span></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p><p class=MsoPlainText><img border=0 width=293 height=239 style='width:3.052in;height:2.4895in' id="Picture_x0020_2" src="cid:image002.jpg@01D7A49D.D8923440"><span style='color:black'><o:p></o:p></span></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p><p class=MsoPlainText><span style='color:black'>Regarding my allusion to the board game Clue: I often wondered why the game makers didn’t seem to have one, with that absurd premise. A detective could easily figure out what room in which Mr. Boddy’s body was discovered, such as by looking around and seeing if she saw pans and dishes (probably kitchen) or if she saw books (might deduce it was the library.) Likewise it should be easy enough to determine whether some perp shot Boddy or swatted him with a candlestick. The corpses look different, depending on the circumstances.<o:p></o:p></span></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p><p class=MsoPlainText><span style='color:black'>Furthermore… what if a Manson follower climbed in the window, smacked Boddy with a lead pipe, then went back out the same window?<o:p></o:p></span></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p><p class=MsoPlainText><span style='color:black'>But hey it’s a game, and actually a fun one. I seldom lost at that. If one gets good at it, there isn’t much guesswork.<o:p></o:p></span></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p><p class=MsoPlainText><span style='color:black'>spike<o:p></o:p></span></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p><p class=MsoPlainText><span style='color:black'><o:p> </o:p></span></p></div></body></html>