<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
		>
<channel>
	<title>Comments on: Google Image Search &#8211; Now By Colour!</title>
	<atom:link href="http://www.bloommedia.co.uk/blog/search-marketing/google-image-search-now-by-colour/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.bloommedia.co.uk/blog/search-marketing/google-image-search-now-by-colour/</link>
	<description>Bloom Media are an award winning 'full service digital agency', we provide ROI focussed digital campaigns for some of the UK's biggest brands.</description>
	<lastBuildDate>Fri, 18 Jun 2010 15:11:19 +0100</lastBuildDate>
	<generator>http://wordpress.org/?v=2.8.2</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: stuartpturner</title>
		<link>http://www.bloommedia.co.uk/blog/search-marketing/google-image-search-now-by-colour/#comment-251</link>
		<dc:creator>stuartpturner</dc:creator>
		<pubDate>Thu, 09 Apr 2009 17:08:12 +0000</pubDate>
		<guid isPermaLink="false">http://www.bloommedia.co.uk/blog/?p=278#comment-251</guid>
		<description>Good call Dom, if Google fulfils it&#039;s threat of proper blended results we might see photos, maps and Street View all becoming one beautiful medly. This has been partially implemented but not to its fullest potential. Didn&#039;t realise cameras were getting location aware, cool but a bit Skynet...

With the addition of facial recognition you could also include filters like &#039;beard&#039;, &#039;moustache&#039; or even &#039;mullet&#039; once things got advanced enough - maybe even down to eye colour or hair colour - imagine that! The stalking possibilites would be massively increased as well though but given the way Google deals with privacy (very seriously) I&#039;m sure they will keepo an eye on it.</description>
		<content:encoded><![CDATA[<p>Good call Dom, if Google fulfils it&#8217;s threat of proper blended results we might see photos, maps and Street View all becoming one beautiful medly. This has been partially implemented but not to its fullest potential. Didn&#8217;t realise cameras were getting location aware, cool but a bit Skynet&#8230;</p>
<p>With the addition of facial recognition you could also include filters like &#8216;beard&#8217;, &#8216;moustache&#8217; or even &#8216;mullet&#8217; once things got advanced enough &#8211; maybe even down to eye colour or hair colour &#8211; imagine that! The stalking possibilites would be massively increased as well though but given the way Google deals with privacy (very seriously) I&#8217;m sure they will keepo an eye on it.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Dominic Kelly</title>
		<link>http://www.bloommedia.co.uk/blog/search-marketing/google-image-search-now-by-colour/#comment-250</link>
		<dc:creator>Dominic Kelly</dc:creator>
		<pubDate>Thu, 09 Apr 2009 13:41:56 +0000</pubDate>
		<guid isPermaLink="false">http://www.bloommedia.co.uk/blog/?p=278#comment-250</guid>
		<description>I would expect precise location to be the next big thing in image search. Most newer camera&#039;s these days are location aware, or can easily be equipped with a GPS dongle. 

For example, in the not so distant future, a search for &quot;historic buildings Leeds&quot; would lookup all images with the location attribute set to &quot;Leeds&quot;, rather than just reading from the filename or human labels.

Also, facial recognition could be easily integrated into image search. Facebook already has it in it&#039;s Photo Albums, and so does Apple&#039;s iPhoto &#039;09. Again, rather than relying on ambiguous filenames or descriptions, it would be nice to be able to find every photo of &quot;Megan Fox&quot; based on actual computed facial recognition, not least because she is ridiculously hot. This does raise all kinds of privacy issues, but if you empower the users with the option then that isn&#039;t really a problem at all.

Check out Yahoo&#039;s image search too. I can&#039;t vouch for it&#039;s accuracy, but the interface is a bit nicer in my opinion.</description>
		<content:encoded><![CDATA[<p>I would expect precise location to be the next big thing in image search. Most newer camera&#8217;s these days are location aware, or can easily be equipped with a GPS dongle. </p>
<p>For example, in the not so distant future, a search for &#8220;historic buildings Leeds&#8221; would lookup all images with the location attribute set to &#8220;Leeds&#8221;, rather than just reading from the filename or human labels.</p>
<p>Also, facial recognition could be easily integrated into image search. Facebook already has it in it&#8217;s Photo Albums, and so does Apple&#8217;s iPhoto &#8216;09. Again, rather than relying on ambiguous filenames or descriptions, it would be nice to be able to find every photo of &#8220;Megan Fox&#8221; based on actual computed facial recognition, not least because she is ridiculously hot. This does raise all kinds of privacy issues, but if you empower the users with the option then that isn&#8217;t really a problem at all.</p>
<p>Check out Yahoo&#8217;s image search too. I can&#8217;t vouch for it&#8217;s accuracy, but the interface is a bit nicer in my opinion.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
