<?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: Cleaning up scanned text</title>
	<atom:link href="http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/feed/" rel="self" type="application/rss+xml" />
	<link>http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/</link>
	<description>Steve Eddins manages the Image &#38; Geospatial development team at The MathWorks and coauthored Digital Image Processing Using MATLAB. He writes here about image processing concepts, algorithm implementations, and MATLAB.</description>
	<lastBuildDate>Sat, 11 Feb 2012 18:27:50 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.2.1</generator>
	<item>
		<title>By: Steve</title>
		<link>http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-24451</link>
		<dc:creator>Steve</dc:creator>
		<pubDate>Fri, 02 Sep 2011 12:05:25 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-24451</guid>
		<description>R&#8212;I don&#039;t know.</description>
		<content:encoded><![CDATA[<p>R&mdash;I don&#8217;t know.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: R Smit</title>
		<link>http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-24450</link>
		<dc:creator>R Smit</dc:creator>
		<pubDate>Fri, 02 Sep 2011 11:46:33 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-24450</guid>
		<description>Wanted to know if anywork was being done on actually cleaning up the text in a scan.  I.e. when the type face is recognized (from say a database) then redaw (totally enhance) the original scan.  Or simply refine the rules for what constitutes a &quot;type face&quot; and use this to clean-up the graphic of scanned text.</description>
		<content:encoded><![CDATA[<p>Wanted to know if anywork was being done on actually cleaning up the text in a scan.  I.e. when the type face is recognized (from say a database) then redaw (totally enhance) the original scan.  Or simply refine the rules for what constitutes a &#8220;type face&#8221; and use this to clean-up the graphic of scanned text.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Steve</title>
		<link>http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-22064</link>
		<dc:creator>Steve</dc:creator>
		<pubDate>Mon, 17 Aug 2009 18:31:12 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-22064</guid>
		<description>Alosha&#8212;I don&#039;t know what that means. Can you clarify?</description>
		<content:encoded><![CDATA[<p>Alosha&mdash;I don&#8217;t know what that means. Can you clarify?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: alosha</title>
		<link>http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-22050</link>
		<dc:creator>alosha</dc:creator>
		<pubDate>Mon, 17 Aug 2009 16:45:06 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-22050</guid>
		<description>hi steve,
could please let me know can i map some text data to the image .. thank you very much</description>
		<content:encoded><![CDATA[<p>hi steve,<br />
could please let me know can i map some text data to the image .. thank you very much</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Steve</title>
		<link>http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-21438</link>
		<dc:creator>Steve</dc:creator>
		<pubDate>Fri, 30 Jan 2009 14:26:08 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-21438</guid>
		<description>Etamar&#8212;I don&#039;t have anything to add to my original answer.  The operations could be readily implemented on a fixed-point processor, but I don&#039;t know how long the operation might take.  Did you really mean &quot;several microseconds&quot;?  I assume you&#039;re not really hoping to process hundreds of thousands of images per second.  :-)</description>
		<content:encoded><![CDATA[<p>Etamar&mdash;I don&#8217;t have anything to add to my original answer.  The operations could be readily implemented on a fixed-point processor, but I don&#8217;t know how long the operation might take.  Did you really mean &#8220;several microseconds&#8221;?  I assume you&#8217;re not really hoping to process hundreds of thousands of images per second.  :-)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Etamar Laron</title>
		<link>http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-21437</link>
		<dc:creator>Etamar Laron</dc:creator>
		<pubDate>Fri, 30 Jan 2009 14:21:55 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-21437</guid>
		<description>Hi guys,

To reopen my old question - do you think this algorithm can be performed in a reasonable (several microseconds) using an inexpensive hardware?

In inexpensive I mean $1 or less 8051 or similar......... not a laptop from three years ago.

Appreciate your thoughts!</description>
		<content:encoded><![CDATA[<p>Hi guys,</p>
<p>To reopen my old question &#8211; do you think this algorithm can be performed in a reasonable (several microseconds) using an inexpensive hardware?</p>
<p>In inexpensive I mean $1 or less 8051 or similar&#8230;&#8230;&#8230; not a laptop from three years ago.</p>
<p>Appreciate your thoughts!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: DP</title>
		<link>http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-20757</link>
		<dc:creator>DP</dc:creator>
		<pubDate>Sat, 31 May 2008 14:42:02 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-20757</guid>
		<description>Thank U.</description>
		<content:encoded><![CDATA[<p>Thank U.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Bob</title>
		<link>http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-20754</link>
		<dc:creator>Bob</dc:creator>
		<pubDate>Fri, 30 May 2008 19:11:17 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-20754</guid>
		<description>DP, you might also check out the follow File Exchange submission for ideas.
http://www.mathworks.com/matlabcentral/fileexchange/loadFile.do?objectId=4879

Cheers
Bob</description>
		<content:encoded><![CDATA[<p>DP, you might also check out the follow File Exchange submission for ideas.<br />
<a href="http://www.mathworks.com/matlabcentral/fileexchange/loadFile.do?objectId=4879" rel="nofollow">http://www.mathworks.com/matlabcentral/fileexchange/loadFile.do?objectId=4879</a></p>
<p>Cheers<br />
Bob</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Steve</title>
		<link>http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-20753</link>
		<dc:creator>Steve</dc:creator>
		<pubDate>Fri, 30 May 2008 17:36:36 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-20753</guid>
		<description>DP&#8212;You could try &lt;tt&gt;montage&lt;/tt&gt;.  You should also look at the 3-D visualization material in the MATLAB documentation.</description>
		<content:encoded><![CDATA[<p>DP&mdash;You could try <tt>montage</tt>.  You should also look at the 3-D visualization material in the MATLAB documentation.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Steve</title>
		<link>http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-20752</link>
		<dc:creator>Steve</dc:creator>
		<pubDate>Fri, 30 May 2008 17:23:41 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.mathworks.com/steve/2007/12/07/cleaning-up-scanned-text/#comment-20752</guid>
		<description>Para&#8212;Complement the image before calling &lt;tt&gt;bwmorph&lt;/tt&gt;.  Use &lt;tt&gt;~&lt;/tt&gt; or &lt;tt&gt;imcomplement&lt;/tt&gt;.</description>
		<content:encoded><![CDATA[<p>Para&mdash;Complement the image before calling <tt>bwmorph</tt>.  Use <tt>~</tt> or <tt>imcomplement</tt>.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

