<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	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/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Ravi Blogs about IT Topics &#187; Facial Recognition</title>
	<atom:link href="http://ravisblog.blogs.wesleyan.edu/tag/facial-recognition/feed/" rel="self" type="application/rss+xml" />
	<link>http://ravisblog.blogs.wesleyan.edu</link>
	<description>Ravi, the Associate VP for ITS, discusses IT topics</description>
	<lastBuildDate>Thu, 25 Jun 2009 11:26:36 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.8.4</generator>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
			<item>
		<title>Facial Recognition in Picasa</title>
		<link>http://ravisblog.blogs.wesleyan.edu/2008/10/14/facial-recognition-in-picasa-2/</link>
		<comments>http://ravisblog.blogs.wesleyan.edu/2008/10/14/facial-recognition-in-picasa-2/#comments</comments>
		<pubDate>Tue, 14 Oct 2008 14:19:46 +0000</pubDate>
		<dc:creator>ravishan</dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[Facial Recognition]]></category>
		<category><![CDATA[Picasa]]></category>
		<category><![CDATA[privacy]]></category>

		<guid isPermaLink="false">http://ravisblog.blogs.wesleyan.edu/?p=152</guid>
		<description><![CDATA[I guard all my photos with the highest level of care that they deserve. I am sure most of you do. The &#8220;born digital&#8221; photos are the easiest to manage in that you download them to your laptop or desktop. I have also been systematically scanning the negatives and photographs from very early on. Now [...]]]></description>
			<content:encoded><![CDATA[<p>I guard all my photos with the highest level of care that they deserve. I am sure most of you do. The &#8220;born digital&#8221; photos are the easiest to manage in that you download them to your laptop or desktop. I have also been systematically scanning the negatives and photographs from very early on. Now that the cold days of winter are upon us, I will begin this exercise and I am confident that I will be done by March or April 2009.</p>
<p>Since I am paranoid about preserving them, I back them up to two separate external disks at home. But to me, that still does not provide all the redundancy that is required. I chose to save them on Picasa web album after some research because of the rich feature set. I have purchased additional disk space because I have exceeded the free offering. The cost is very reasonable, so I don&#8217;t mind.<span id="more-152"></span></p>
<p>I wrote about how I try to tag them as much as I can. I have done GeoTagging the pictures during our two most recent trips to Europe. But this is a very long process. This is why I was thrilled with the &#8220;Opt in&#8221; feature of Name Tagging. When you sign up to Name Tag your pictures, a background process runs to identify the faces on all pictures. After this, you can use the web interface to tag the names of people.</p>
<p>The systems seems to be pretty good in clustering faces of the person from multiple albums at various angles. So, for example, in one shot you can identify the person in 25 pictures by tagging the person. Of course, it is unable to present <strong>ALL</strong> faces from all albums of a person in one shot, though that would have been nice. Whatever similarity algorithm they use, seems to cluster the faces. So, for example, my face appears in many different clusters. What was impressive was, after I tag myself in one cluster and move to the next, it provides me with three choices of possible matches and in most cases, one of them happens to be me. In other words, its suggestions across clusters seems to be pretty good.</p>
<p>This is a really powerful feature that has vastly simplified my task of tagging and finding all photos of a person easily. I love it&#8230;</p>
<p>Of course, there are serious privacy concerns around this in terms of how this will be used by Google and possibly by law enforcement. For example, is Google going to gather the information about my friends and profile me in ways that then benefits their business operation? For example, would it find that most of my friends are of Indian descent and flash cheap tickets to India when I log in? You can extend this in other ominous ways.</p>
<p>Would the law enforcement issue subpoena to Google to reveal this database to identify all those who may be connected to a suspected criminal? Of course information like this can be gathered in ways other than facial recognition and related correlations, but this would be an additional source of data.</p>
<p>I know that these are extremely important questions and the level of comfort that one feels towards these will enetually drive whether someone wants to take advantage of these features or not. For now I have decided to use them&#8230;</p>
]]></content:encoded>
			<wfw:commentRss>http://ravisblog.blogs.wesleyan.edu/2008/10/14/facial-recognition-in-picasa-2/feed/</wfw:commentRss>
		<slash:comments>1</slash:comments>
		</item>
	</channel>
</rss>
