<?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: Fields related to Computer Vision, part 3</title>
	<atom:link href="http://inperc.com/blog2/index.php/2008/03/28/fields-related-to-computer-vision-part-3/feed/" rel="self" type="application/rss+xml" />
	<link>http://inperc.com/blog2/2008/03/28/fields-related-to-computer-vision-part-3/</link>
	<description>Computer vision and image analysis for newcomers</description>
	<lastBuildDate>Wed, 27 Jan 2010 21:13:46 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.2</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: Computer Vision for Dummies &#187; Google&#8217;s new image search</title>
		<link>http://inperc.com/blog2/2008/03/28/fields-related-to-computer-vision-part-3/comment-page-1/#comment-198</link>
		<dc:creator>Computer Vision for Dummies &#187; Google&#8217;s new image search</dc:creator>
		<pubDate>Tue, 29 Apr 2008 19:34:40 +0000</pubDate>
		<guid isPermaLink="false">http://inperc.com/blog2/2008/03/28/fields-related-to-computer-vision-part-3/#comment-198</guid>
		<description>[...] The most important thing to understand here is that the paper isn’t about improving image search in general (especially visual image search and CBIR, see here). It is specifically about Google image search (and indirectly other search engines, MSN, Yahoo, etc). The goal is to improve it (because it sucks). It is currently based on surrounding text and as a result you get a lot of irrelevant images. Essentially, they add to this approach some image analysis. What kind? Not the best kind – “descriptors”. So there will be no analysis of the content of the image (see Fields related to computer vision). Even so, the descriptors will help to evaluate similarity between images - to a certain degree. [...]</description>
		<content:encoded><![CDATA[<p>[...] The most important thing to understand here is that the paper isn’t about improving image search in general (especially visual image search and CBIR, see here). It is specifically about Google image search (and indirectly other search engines, MSN, Yahoo, etc). The goal is to improve it (because it sucks). It is currently based on surrounding text and as a result you get a lot of irrelevant images. Essentially, they add to this approach some image analysis. What kind? Not the best kind – “descriptors”. So there will be no analysis of the content of the image (see Fields related to computer vision). Even so, the descriptors will help to evaluate similarity between images &#8211; to a certain degree. [...]</p>
]]></content:encoded>
	</item>
</channel>
</rss>
