<?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: Idea: Book recommender</title>
	<atom:link href="http://nat.org/blog/2009/11/idea-book-recommender/feed/" rel="self" type="application/rss+xml" />
	<link>http://nat.org/blog/2009/11/idea-book-recommender/</link>
	<description></description>
	<lastBuildDate>Wed, 10 Mar 2010 13:53:22 +0100</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.1</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: Luis</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5735</link>
		<dc:creator>Luis</dc:creator>
		<pubDate>Wed, 04 Nov 2009 09:58:29 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5735</guid>
		<description>The recommendations side is almost certainly librarything, though I believe Amazon will now also give you recommendations on things you didn&#039;t buy there. As for the rest, my current plan is to scan everything as I unpack it when I get out of storage at the end of the honeymoon :)</description>
		<content:encoded><![CDATA[<p>The recommendations side is almost certainly librarything, though I believe Amazon will now also give you recommendations on things you didn&#8217;t buy there. As for the rest, my current plan is to scan everything as I unpack it when I get out of storage at the end of the honeymoon <img src='http://nat.org/blog/wp-includes/images/smilies/icon_smile.gif' alt=':)' class='wp-smiley' /> </p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Ian McKellar</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5715</link>
		<dc:creator>Ian McKellar</dc:creator>
		<pubDate>Tue, 03 Nov 2009 18:19:39 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5715</guid>
		<description>Why stop at books, surely it can&#039;t take that much computing (or mechanical turk) to identify and recommend stuff.


Also, it should be able to recommend living rooms to thieves.</description>
		<content:encoded><![CDATA[<p>Why stop at books, surely it can&#8217;t take that much computing (or mechanical turk) to identify and recommend stuff.</p>
<p>Also, it should be able to recommend living rooms to thieves.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Io McKinnon</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5709</link>
		<dc:creator>Io McKinnon</dc:creator>
		<pubDate>Tue, 03 Nov 2009 16:15:12 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5709</guid>
		<description>Didn&#039;t take long for someone to catch up:

Registrant:
   c/o BOOKSCANR.COM
   P.O. Box 821650
   Vancouver, WA  98682
   US

   Registrar: DOTSTER</description>
		<content:encoded><![CDATA[<p>Didn&#8217;t take long for someone to catch up:</p>
<p>Registrant:<br />
   c/o BOOKSCANR.COM<br />
   P.O. Box 821650<br />
   Vancouver, WA  98682<br />
   US</p>
<p>   Registrar: DOTSTER</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Wolfgang</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5701</link>
		<dc:creator>Wolfgang</dc:creator>
		<pubDate>Tue, 03 Nov 2009 12:57:07 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5701</guid>
		<description>http://ideas.4brad.com/photograph-your-shelves-catalog-your-library</description>
		<content:encoded><![CDATA[<p><a href="http://ideas.4brad.com/photograph-your-shelves-catalog-your-library" rel="nofollow">http://ideas.4brad.com/photograph-your-shelves-catalog-your-library</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Wolfgang</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5700</link>
		<dc:creator>Wolfgang</dc:creator>
		<pubDate>Tue, 03 Nov 2009 12:21:53 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5700</guid>
		<description>Wow, that is a cool idea! There are lots of good book-communities out there which allow you to add all your books to some kind of virtual shelf (e.g. lovelybooks, goodreads, librarything). But who wants to add 100s of books manually... The coolest thing would be to integrate such an OCR-approach into one of those sides. Or maybe, if some of you are interested, we could develop such an OCR-book-scanner and see what we can do with it.</description>
		<content:encoded><![CDATA[<p>Wow, that is a cool idea! There are lots of good book-communities out there which allow you to add all your books to some kind of virtual shelf (e.g. lovelybooks, goodreads, librarything). But who wants to add 100s of books manually&#8230; The coolest thing would be to integrate such an OCR-approach into one of those sides. Or maybe, if some of you are interested, we could develop such an OCR-book-scanner and see what we can do with it.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: oliver</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5694</link>
		<dc:creator>oliver</dc:creator>
		<pubDate>Tue, 03 Nov 2009 10:22:17 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5694</guid>
		<description>PS: would it be possible to make a &quot;movie&quot; of the shelf, ie. moving the phone on front of the shelf and letting some software stitch the frames into a huge multi-megapixel image? Could current panorama stitching software be used for this?</description>
		<content:encoded><![CDATA[<p>PS: would it be possible to make a &#8220;movie&#8221; of the shelf, ie. moving the phone on front of the shelf and letting some software stitch the frames into a huge multi-megapixel image? Could current panorama stitching software be used for this?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: oliver</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5693</link>
		<dc:creator>oliver</dc:creator>
		<pubDate>Tue, 03 Nov 2009 10:16:41 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5693</guid>
		<description>The book spine OCRing would be really useful, just to get a digital list of one&#039;s own book shelf. What is the current state of free OCR engines?</description>
		<content:encoded><![CDATA[<p>The book spine OCRing would be really useful, just to get a digital list of one&#8217;s own book shelf. What is the current state of free OCR engines?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Ben Maurer</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5677</link>
		<dc:creator>Ben Maurer</dc:creator>
		<pubDate>Tue, 03 Nov 2009 03:36:32 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5677</guid>
		<description>Doing the OCR would be hardish. It&#039;s probably solvable to some extent, but definitely not by off the shelf software. I think the amazon referral fees could be worth enough that it&#039;d make sense to mturk the problem (doing text detection is much easier than accurately digitizing it). This is especially true if you progressively catalog the user&#039;s library as they start buying books based on your referrals (so that you don&#039;t spend tons of money on unprofitable users).</description>
		<content:encoded><![CDATA[<p>Doing the OCR would be hardish. It&#8217;s probably solvable to some extent, but definitely not by off the shelf software. I think the amazon referral fees could be worth enough that it&#8217;d make sense to mturk the problem (doing text detection is much easier than accurately digitizing it). This is especially true if you progressively catalog the user&#8217;s library as they start buying books based on your referrals (so that you don&#8217;t spend tons of money on unprofitable users).</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jonathan Hernandez</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5676</link>
		<dc:creator>Jonathan Hernandez</dc:creator>
		<pubDate>Tue, 03 Nov 2009 03:31:31 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5676</guid>
		<description>Sounds good, I dont know if &quot;Amazon Remembers&quot; (Amazon iPhone app) has an API, it could be used for that idea, Amazon already has the recommendation engine, the problem here is the app to identify the distinct books (or maybe it can be used for all the things in your room)</description>
		<content:encoded><![CDATA[<p>Sounds good, I dont know if &#8220;Amazon Remembers&#8221; (Amazon iPhone app) has an API, it could be used for that idea, Amazon already has the recommendation engine, the problem here is the app to identify the distinct books (or maybe it can be used for all the things in your room)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Nat Friedman</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5661</link>
		<dc:creator>Nat Friedman</dc:creator>
		<pubDate>Mon, 02 Nov 2009 21:41:53 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5661</guid>
		<description>Jered, Chris

I think a standard non-phone camera should be able to get enough information from each spine to make it identifiable. You don&#039;t have to actually be able to read each character, but I bet you can learn to identify books by spine. There could be some kind of guideline like &quot;30 books per picture, 5MP minimum.&quot;

And anyway, there&#039;s no way I am going to scan the barcodes of my 100s of books. I don&#039;t know about you guys but I&#039;m not sitting on a lot of afternoons where I think to myself &quot;You know what I want to do right now? Scan barcodes for 5 hours.&quot;</description>
		<content:encoded><![CDATA[<p>Jered, Chris</p>
<p>I think a standard non-phone camera should be able to get enough information from each spine to make it identifiable. You don&#8217;t have to actually be able to read each character, but I bet you can learn to identify books by spine. There could be some kind of guideline like &#8220;30 books per picture, 5MP minimum.&#8221;</p>
<p>And anyway, there&#8217;s no way I am going to scan the barcodes of my 100s of books. I don&#8217;t know about you guys but I&#8217;m not sitting on a lot of afternoons where I think to myself &#8220;You know what I want to do right now? Scan barcodes for 5 hours.&#8221;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Kelly Clowers</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5660</link>
		<dc:creator>Kelly Clowers</dc:creator>
		<pubDate>Mon, 02 Nov 2009 21:36:53 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5660</guid>
		<description>just use LibraryThing and a cuecat</description>
		<content:encoded><![CDATA[<p>just use LibraryThing and a cuecat</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Chris</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5658</link>
		<dc:creator>Chris</dc:creator>
		<pubDate>Mon, 02 Nov 2009 21:19:57 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5658</guid>
		<description>I don&#039;t think the OCR is going to work out; you just aren&#039;t going to have enough pixels dedicated to each book, even with a good camera which most people don&#039;t have, and current state of the art OCR needs crisp black text on a white background and so on.

The approach that seems more promising to me is using cell phone cameras to scan the barcodes of each book to build a library that way -- see e.g. http://www.brendonwilson.com/blog/tag/barcode-scanner/ for a barcode-to-Shelfari client, or you can use a mix of Barcode Scanner and Clipbot on an Android phone.

-- cjb.</description>
		<content:encoded><![CDATA[<p>I don&#8217;t think the OCR is going to work out; you just aren&#8217;t going to have enough pixels dedicated to each book, even with a good camera which most people don&#8217;t have, and current state of the art OCR needs crisp black text on a white background and so on.</p>
<p>The approach that seems more promising to me is using cell phone cameras to scan the barcodes of each book to build a library that way &#8212; see e.g. <a href="http://www.brendonwilson.com/blog/tag/barcode-scanner/" rel="nofollow">http://www.brendonwilson.com/blog/tag/barcode-scanner/</a> for a barcode-to-Shelfari client, or you can use a mix of Barcode Scanner and Clipbot on an Android phone.</p>
<p>&#8211; cjb.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jered Floyd</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5656</link>
		<dc:creator>Jered Floyd</dc:creator>
		<pubDate>Mon, 02 Nov 2009 20:49:56 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5656</guid>
		<description>I like the idea, although even assuming a good OCR engine that can deal with wild spines, this&#039;ll require dozens to hundreds of photos to get enough resolution.  As long as they can be easily uploaded, I guess that&#039;s not a big deal.</description>
		<content:encoded><![CDATA[<p>I like the idea, although even assuming a good OCR engine that can deal with wild spines, this&#8217;ll require dozens to hundreds of photos to get enough resolution.  As long as they can be easily uploaded, I guess that&#8217;s not a big deal.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Nat Friedman</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5653</link>
		<dc:creator>Nat Friedman</dc:creator>
		<pubDate>Mon, 02 Nov 2009 19:27:22 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5653</guid>
		<description>Actually one of my bookshelves is but it doesn&#039;t look nearly that good

http://www.flickr.com/photos/natfriedman/3334231470/

The photo is from flickr.</description>
		<content:encoded><![CDATA[<p>Actually one of my bookshelves is but it doesn&#8217;t look nearly that good</p>
<p><a href="http://www.flickr.com/photos/natfriedman/3334231470/" rel="nofollow">http://www.flickr.com/photos/natfriedman/3334231470/</a></p>
<p>The photo is from flickr.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Matt McClure</title>
		<link>http://nat.org/blog/2009/11/idea-book-recommender/comment-page-1/#comment-5652</link>
		<dc:creator>Matt McClure</dc:creator>
		<pubDate>Mon, 02 Nov 2009 19:25:18 +0000</pubDate>
		<guid isPermaLink="false">http://nat.org/blog/?p=1415#comment-5652</guid>
		<description>Is your bookshelf organized by spine color?  Or is that a stock image?  Or lighting?</description>
		<content:encoded><![CDATA[<p>Is your bookshelf organized by spine color?  Or is that a stock image?  Or lighting?</p>
]]></content:encoded>
	</item>
</channel>
</rss>
