<?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: Giving Up on Picasa Face Recognition</title>
	<atom:link href="http://regex.info/blog/2009-12-07/1388/feed" rel="self" type="application/rss+xml" />
	<link>http://regex.info/blog/2009-12-07/1388</link>
	<description>Not a photo blog. A personal blog with photos.</description>
	<lastBuildDate>Wed, 23 May 2012 12:55:23 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.2</generator>
	<item>
		<title>By: Aaron Rothschild</title>
		<link>http://regex.info/blog/2009-12-07/1388#comment-42113</link>
		<dc:creator>Aaron Rothschild</dc:creator>
		<pubDate>Fri, 11 Feb 2011 16:39:22 +0000</pubDate>
		<guid isPermaLink="false">http://regex.info/blog/2009-12-07/1388#comment-42113</guid>
		<description>Jeffrey,

The other day I came across an article about Face.com that provides facial recognition as a service - and they provide a free service for up to 120,000 images per day (5,000 per hour).  Facebook uses them as a provider in their backend.  It seems like it may suit your needs if you are still interested in this sort of thing.

http://developers.face.com/docs/

Aaron
San Francisco, CA
Picture Site:&lt;a href=&quot;http://www.rothytography.com&quot; rel=&quot;nofollow&quot;&gt;www.rothytography.com&lt;/a&gt;</description>
		<content:encoded><![CDATA[<p>Jeffrey,</p>
<p>The other day I came across an article about Face.com that provides facial recognition as a service &#8211; and they provide a free service for up to 120,000 images per day (5,000 per hour).  Facebook uses them as a provider in their backend.  It seems like it may suit your needs if you are still interested in this sort of thing.</p>
<p><a href="http://developers.face.com/docs/" rel="nofollow">http://developers.face.com/docs/</a></p>
<p>Aaron<br />
San Francisco, CA<br />
Picture Site:<a href="http://www.rothytography.com" rel="nofollow">http://www.rothytography.com</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Dan</title>
		<link>http://regex.info/blog/2009-12-07/1388#comment-37656</link>
		<dc:creator>Dan</dc:creator>
		<pubDate>Thu, 24 Dec 2009 13:33:37 +0000</pubDate>
		<guid isPermaLink="false">http://regex.info/blog/2009-12-07/1388#comment-37656</guid>
		<description>Jeffrey,

I think I got along better with the UI than you, mainly by multi-selecting wrongly identified faces and then right click/moving them to the correct people. But it certainly shows all the signs of a first release...

Dan</description>
		<content:encoded><![CDATA[<p>Jeffrey,</p>
<p>I think I got along better with the UI than you, mainly by multi-selecting wrongly identified faces and then right click/moving them to the correct people. But it certainly shows all the signs of a first release&#8230;</p>
<p>Dan</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Michael Nielsen</title>
		<link>http://regex.info/blog/2009-12-07/1388#comment-37560</link>
		<dc:creator>Michael Nielsen</dc:creator>
		<pubDate>Mon, 14 Dec 2009 15:45:51 +0000</pubDate>
		<guid isPermaLink="false">http://regex.info/blog/2009-12-07/1388#comment-37560</guid>
		<description>Hi Jeffrey,

Please read:
http://forums.adobe.com/thread/538646?tstart=0

I keep the information in XMP, not writing any information to the NEF/JPG files.

And if you are interested in joining forces on this project, get in touch with me. There are of course some issues of Picasa naming the ppl wrong, and that being inserted to the file.

I&#039;ve looked into making it a true Lightroom plugin, but that will take some time - So for now its a 3 step process as described at the above link.

Best regards,
Michael</description>
		<content:encoded><![CDATA[<p>Hi Jeffrey,</p>
<p>Please read:<br />
<a href="http://forums.adobe.com/thread/538646?tstart=0" rel="nofollow">http://forums.adobe.com/thread/538646?tstart=0</a></p>
<p>I keep the information in XMP, not writing any information to the NEF/JPG files.</p>
<p>And if you are interested in joining forces on this project, get in touch with me. There are of course some issues of Picasa naming the ppl wrong, and that being inserted to the file.</p>
<p>I&#8217;ve looked into making it a true Lightroom plugin, but that will take some time &#8211; So for now its a 3 step process as described at the above link.</p>
<p>Best regards,<br />
Michael</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: BKKPhotographer</title>
		<link>http://regex.info/blog/2009-12-07/1388#comment-37535</link>
		<dc:creator>BKKPhotographer</dc:creator>
		<pubDate>Sat, 12 Dec 2009 12:21:51 +0000</pubDate>
		<guid isPermaLink="false">http://regex.info/blog/2009-12-07/1388#comment-37535</guid>
		<description>It was an experiment to see how best to use the very cool tool on a large number of photos. I don&#039;t went to try and recognize every face in every photo I have taken. I already use Lightroom keywords to tag pictures of F&amp;F so I don&#039;t think I have a major use for it. But it seemed fun to try.

I bet a lot has been researched on face recognition technology. Are surveillance cameras common in Japan as they are in the UK? There are very few here in Thailand.

&lt;span class=&#039;jfriedl&#039;&gt;Surveillance cameras are common in stores and banks and such, though I&#039;ve never noticed one in public like they have in the UK.  Fifteen or so years ago I was wandering around one of the labs at the central research site of my company (Omron Tateishi Denki) and noticed some license-plate recognition stuff being tested. A camera had been mounted over the street, pointing mostly down, zoomed up fairly strongly to capture the bulk of one lane. As a car would flash by through the field of view, the system would isolate the license plate, decode it, and display the number faster than I could myself find the license plate. It was very impressive. (This system is used today to predict traffic times... you&#039;ll see a big sign over the road telling you how long it will take to get to such and such a spot via what kind of route.... they keep track of license plates that passed the location, then passed various intermediate locations, then the destination location, and compute the times. Unbelievably, it is not used for speed enforcement.)   A friend here in Kyoto (Britto) has worked on face recognition hardware for cameras... I&#039;m surprised he hasn&#039;t commented yet. I&#039;ll have to ask him about it.... &#8212;Jeffrey&lt;/span&gt;</description>
		<content:encoded><![CDATA[<p>It was an experiment to see how best to use the very cool tool on a large number of photos. I don&#8217;t went to try and recognize every face in every photo I have taken. I already use Lightroom keywords to tag pictures of F&#038;F so I don&#8217;t think I have a major use for it. But it seemed fun to try.</p>
<p>I bet a lot has been researched on face recognition technology. Are surveillance cameras common in Japan as they are in the UK? There are very few here in Thailand.</p>
<p><span class='jfriedl'>Surveillance cameras are common in stores and banks and such, though I&#8217;ve never noticed one in public like they have in the UK.  Fifteen or so years ago I was wandering around one of the labs at the central research site of my company (Omron Tateishi Denki) and noticed some license-plate recognition stuff being tested. A camera had been mounted over the street, pointing mostly down, zoomed up fairly strongly to capture the bulk of one lane. As a car would flash by through the field of view, the system would isolate the license plate, decode it, and display the number faster than I could myself find the license plate. It was very impressive. (This system is used today to predict traffic times&#8230; you&#8217;ll see a big sign over the road telling you how long it will take to get to such and such a spot via what kind of route&#8230;. they keep track of license plates that passed the location, then passed various intermediate locations, then the destination location, and compute the times. Unbelievably, it is not used for speed enforcement.)   A friend here in Kyoto (Britto) has worked on face recognition hardware for cameras&#8230; I&#8217;m surprised he hasn&#8217;t commented yet. I&#8217;ll have to ask him about it&#8230;. &mdash;Jeffrey</span></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: BKKPhotographer</title>
		<link>http://regex.info/blog/2009-12-07/1388#comment-37527</link>
		<dc:creator>BKKPhotographer</dc:creator>
		<pubDate>Fri, 11 Dec 2009 14:51:11 +0000</pubDate>
		<guid isPermaLink="false">http://regex.info/blog/2009-12-07/1388#comment-37527</guid>
		<description>I read your experiences with Picasa face recognition and decided to try a different approach.

I selected about 50 friends and family and selected about 500 pictures total in Lightroom that contained their images in different poses. I exported them as 600 x 800 96dpi JPG files to a new directory.

I set Picasa to work on them and identified the people whom I care about. As it was a small number of pictures with a few people Picasa processed them in less than 10 minutes.

It was pretty easy to establish names for my top 50 and then drag unknown pictures to those names. I did see one problem that it kept on showing me faces I am sure I told it to ignore. But apart from that the manual work in Picasa was quick.

By doing this I hoped to train Picasa to recognise the people I care most about. My next step when I have time is to point Picasa at all my photos. I hope it will have a high success rate identifying my Top 50 and I want to be able tell it to ignore the rest.

But I am worried that Picasa will confuse Lightroom by altering the master image files so I have not tried it yet.

What do you think of this approach?

Ian Fuller in Bangkok, Thailand.

&lt;span class=&#039;jfriedl&#039;&gt;Since I know nothing about how their face recognition works (I say &quot;their&quot; as if I know how any face recognition works :-) ), I don&#039;t know whether the &quot;training&quot; actually matters, but it seems to make sense. But with this scheme, how do you intend to use the results? &#8212;Jeffrey&lt;/span&gt;</description>
		<content:encoded><![CDATA[<p>I read your experiences with Picasa face recognition and decided to try a different approach.</p>
<p>I selected about 50 friends and family and selected about 500 pictures total in Lightroom that contained their images in different poses. I exported them as 600 x 800 96dpi JPG files to a new directory.</p>
<p>I set Picasa to work on them and identified the people whom I care about. As it was a small number of pictures with a few people Picasa processed them in less than 10 minutes.</p>
<p>It was pretty easy to establish names for my top 50 and then drag unknown pictures to those names. I did see one problem that it kept on showing me faces I am sure I told it to ignore. But apart from that the manual work in Picasa was quick.</p>
<p>By doing this I hoped to train Picasa to recognise the people I care most about. My next step when I have time is to point Picasa at all my photos. I hope it will have a high success rate identifying my Top 50 and I want to be able tell it to ignore the rest.</p>
<p>But I am worried that Picasa will confuse Lightroom by altering the master image files so I have not tried it yet.</p>
<p>What do you think of this approach?</p>
<p>Ian Fuller in Bangkok, Thailand.</p>
<p><span class='jfriedl'>Since I know nothing about how their face recognition works (I say &#8220;their&#8221; as if I know how any face recognition works <img src='http://regex.info/blog/wp-includes/images/smilies/icon_smile.gif' alt=':-)' class='wp-smiley' />  ), I don&#8217;t know whether the &#8220;training&#8221; actually matters, but it seems to make sense. But with this scheme, how do you intend to use the results? &mdash;Jeffrey</span></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: ina</title>
		<link>http://regex.info/blog/2009-12-07/1388#comment-37509</link>
		<dc:creator>ina</dc:creator>
		<pubDate>Wed, 09 Dec 2009 12:42:57 +0000</pubDate>
		<guid isPermaLink="false">http://regex.info/blog/2009-12-07/1388#comment-37509</guid>
		<description>Very good point about the potential to destroy the image-authentification signature.  In my case, however, I always save the original file (for safekeeping) to an external disk before doing anything to the copy.  
 
In a &quot;perfect world.&quot; Adobe would be able to offer facial recognition built-in to Lightroom, and this wouldn&#039;t be an issue. :-)

Thanks,
Ina</description>
		<content:encoded><![CDATA[<p>Very good point about the potential to destroy the image-authentification signature.  In my case, however, I always save the original file (for safekeeping) to an external disk before doing anything to the copy.  </p>
<p>In a &#8220;perfect world.&#8221; Adobe would be able to offer facial recognition built-in to Lightroom, and this wouldn&#8217;t be an issue. <img src='http://regex.info/blog/wp-includes/images/smilies/icon_smile.gif' alt=':-)' class='wp-smiley' /> </p>
<p>Thanks,<br />
Ina</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: ina</title>
		<link>http://regex.info/blog/2009-12-07/1388#comment-37504</link>
		<dc:creator>ina</dc:creator>
		<pubDate>Tue, 08 Dec 2009 22:31:32 +0000</pubDate>
		<guid isPermaLink="false">http://regex.info/blog/2009-12-07/1388#comment-37504</guid>
		<description>My thought about a workflow for Picasa facial recognition was to download the files fresh out of the camera  into a temporary folder in Picasa on a one-time only basis.  I would then do the facial recognition and tag the folders and then right away mport them into Lightroom and read the metadata from the files.  After that I would geoencode  them and do whatever  I normally do in ligthroom.  At that time I would a;so delete the folder index from Picasa, so that the only access to the files would be through Lightroom and Photoshop.  

In other words I would use Picasa ONLY for facial recognition on files fresh from the camera and before embedding any other info into the files.  

Do you think this proposed workflow would work or are you suggesting that  Picasa &quot;corrupts&quot; or  the files in some way???

&lt;span class=&#039;jfriedl&#039;&gt;Some people prefer their image files to never be changed (the whole &quot;non-destructive workflow&quot; concept). In my case, any change (by any application, for any reason) to the contents of my Nikon NEF files destroys the image-authentication signature. (I don&#039;t even know for sure whether Picasa would try to write them, but I didn&#039;t want to take a chance).  If you don&#039;t have the &quot;files are immutable&quot; constraint , then it&#039;s a nice feature if it writes the data directly to the file.... it&#039;s certainly most convenient that way. &#8212;Jeffrey&lt;/span&gt;</description>
		<content:encoded><![CDATA[<p>My thought about a workflow for Picasa facial recognition was to download the files fresh out of the camera  into a temporary folder in Picasa on a one-time only basis.  I would then do the facial recognition and tag the folders and then right away mport them into Lightroom and read the metadata from the files.  After that I would geoencode  them and do whatever  I normally do in ligthroom.  At that time I would a;so delete the folder index from Picasa, so that the only access to the files would be through Lightroom and Photoshop.  </p>
<p>In other words I would use Picasa ONLY for facial recognition on files fresh from the camera and before embedding any other info into the files.  </p>
<p>Do you think this proposed workflow would work or are you suggesting that  Picasa &#8220;corrupts&#8221; or  the files in some way???</p>
<p><span class='jfriedl'>Some people prefer their image files to never be changed (the whole &#8220;non-destructive workflow&#8221; concept). In my case, any change (by any application, for any reason) to the contents of my Nikon NEF files destroys the image-authentication signature. (I don&#8217;t even know for sure whether Picasa would try to write them, but I didn&#8217;t want to take a chance).  If you don&#8217;t have the &#8220;files are immutable&#8221; constraint , then it&#8217;s a nice feature if it writes the data directly to the file&#8230;. it&#8217;s certainly most convenient that way. &mdash;Jeffrey</span></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: ina</title>
		<link>http://regex.info/blog/2009-12-07/1388#comment-37500</link>
		<dc:creator>ina</dc:creator>
		<pubDate>Tue, 08 Dec 2009 09:36:35 +0000</pubDate>
		<guid isPermaLink="false">http://regex.info/blog/2009-12-07/1388#comment-37500</guid>
		<description>I was looking forward to your proposed use of Picasa for facial recognition  and am disappointed to hear of the randomization problems.  I shun iPhoto because of the way it takes command of the any photos showing up in iPhoto.  Picasa seems to be kinder, as it only indexes the files for its own use.

&lt;span class=&#039;jfriedl&#039;&gt;Be careful with Picasa in this regard... I believe it does try to write data to the photos if it can. Prior to invoking Picasa, I made sure that all image files were read only, and that I had a full backup, just in case. &#8212;Jeffrey&lt;/span&gt;</description>
		<content:encoded><![CDATA[<p>I was looking forward to your proposed use of Picasa for facial recognition  and am disappointed to hear of the randomization problems.  I shun iPhoto because of the way it takes command of the any photos showing up in iPhoto.  Picasa seems to be kinder, as it only indexes the files for its own use.</p>
<p><span class='jfriedl'>Be careful with Picasa in this regard&#8230; I believe it does try to write data to the photos if it can. Prior to invoking Picasa, I made sure that all image files were read only, and that I had a full backup, just in case. &mdash;Jeffrey</span></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Bill</title>
		<link>http://regex.info/blog/2009-12-07/1388#comment-37498</link>
		<dc:creator>Bill</dc:creator>
		<pubDate>Tue, 08 Dec 2009 06:40:19 +0000</pubDate>
		<guid isPermaLink="false">http://regex.info/blog/2009-12-07/1388#comment-37498</guid>
		<description>I haven&#039;t seen the same, but honestly, I played with a much smaller set of photos.  The only issue I personally noticed happy with baby photos (of my niece &amp; nephew, when they were both under a year -- somewhat reasonable).

The Picasa team is pretty solid.  I&#039;ll ping them to see if they know about the randomization issue.</description>
		<content:encoded><![CDATA[<p>I haven&#8217;t seen the same, but honestly, I played with a much smaller set of photos.  The only issue I personally noticed happy with baby photos (of my niece &amp; nephew, when they were both under a year &#8212; somewhat reasonable).</p>
<p>The Picasa team is pretty solid.  I&#8217;ll ping them to see if they know about the randomization issue.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Wayne</title>
		<link>http://regex.info/blog/2009-12-07/1388#comment-37496</link>
		<dc:creator>Wayne</dc:creator>
		<pubDate>Mon, 07 Dec 2009 19:03:20 +0000</pubDate>
		<guid isPermaLink="false">http://regex.info/blog/2009-12-07/1388#comment-37496</guid>
		<description>At the risk of sounding obvious and maybe you mentioned this in the past but iPhoto 09?
Its on your new iMac and is supposed to do this superbly.
I tested it and it seemed very accurate.</description>
		<content:encoded><![CDATA[<p>At the risk of sounding obvious and maybe you mentioned this in the past but iPhoto 09?<br />
Its on your new iMac and is supposed to do this superbly.<br />
I tested it and it seemed very accurate.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

