<?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: Pattern recognition in computer vision, part 1</title>
	<atom:link href="http://inperc.com/blog2/index.php/2008/05/02/pattern-recognition-in-computer-vision-part-1/feed/" rel="self" type="application/rss+xml" />
	<link>http://inperc.com/blog2/2008/05/02/pattern-recognition-in-computer-vision-part-1/</link>
	<description>Computer vision, image analysis, and related mathematics</description>
	<lastBuildDate>Thu, 17 Feb 2011 13:25:51 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.1.3</generator>
	<item>
		<title>By: Computer Vision for Dummies &#187; Pattern recognition in computer vision, part 2</title>
		<link>http://inperc.com/blog2/2008/05/02/pattern-recognition-in-computer-vision-part-1/comment-page-1/#comment-209</link>
		<dc:creator>Computer Vision for Dummies &#187; Pattern recognition in computer vision, part 2</dc:creator>
		<pubDate>Mon, 12 May 2008 18:31:54 +0000</pubDate>
		<guid isPermaLink="false">http://inperc.com/blog2/2008/05/02/pattern-recognition-in-computer-vision-part-1/#comment-209</guid>
		<description>[...] Let’s review part 1 first. If you have a 100&#215;100 gray scale image, it is simply a table of 100&#215;100 = 10,000 numbers. You rearrange the rows of this table into a 10,000-vector and represent the image as a point in the 10,000-dimensional Euclidean space. This enables you to measure distances between images, discover patterns, match images, etc. Now, what is wrong with this approach? [...]</description>
		<content:encoded><![CDATA[<p>[...] Let’s review part 1 first. If you have a 100&#215;100 gray scale image, it is simply a table of 100&#215;100 = 10,000 numbers. You rearrange the rows of this table into a 10,000-vector and represent the image as a point in the 10,000-dimensional Euclidean space. This enables you to measure distances between images, discover patterns, match images, etc. Now, what is wrong with this approach? [...]</p>
]]></content:encoded>
	</item>
</channel>
</rss>

