<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=utf-8">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<small>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style><head>
<style></style> </small>
<table class="backgroundTable" cellpadding="0" cellspacing="0"
bgcolor="#ffffff" width="100%">
<tbody>
<tr>
<td align="left" valign="top">
<table cellpadding="0" cellspacing="0">
<tbody>
<tr>
<td style="border-top: 0px solid rgb(0, 0, 0);
border-bottom: 1px solid rgb(255, 255, 255);
background-color: rgb(255, 255, 255); text-align:
center;" align="center"><span style="font-size:
10px; color: rgb(96, 96, 96); line-height: 200%;
font-family: verdana; text-decoration: none;">Email
not
displaying correctly? <a
href="http://www.oplin.org/4cast/"
style="font-size: 10px; color: rgb(0, 0, 255);
line-height: 200%; font-family: verdana;
text-decoration: none;">View
it in your browser.</a></span></td>
</tr>
<tr>
<td style="border-top: 0px solid rgb(51, 51, 51);
border-bottom: 0px solid rgb(255, 255, 255);
background-color: rgb(255, 255, 255);">
<center><a href=""><img id="editableImg1"
src="cid:part2.00090106.00000008@oplin.org"
title="OPLIN" alt="OPLIN 4Cast" border="0"
align="middle"></a></center>
</td>
</tr>
</tbody>
</table>
<table style="width: 763px; height: 877px;" cellpadding="20"
cellspacing="0" bgcolor="#ffffff">
<tbody>
<tr>
<td style="font-size: 12px; color: rgb(0, 0, 0);
line-height: 150%; font-family: trebuchet ms;"
background="http://www.oplin.org/4cast/wp-content/themes/4cast/images/kubrickbgwide.jpg"
bgcolor="#ffffff" valign="top">
<p><!-- Make sure you modify the 4Cast title in this section -->
<span style="font-size: 20px; font-weight: bold;
color: rgb(0, 0, 0); font-family: arial;
line-height: 110%;">OPLIN 4cast #414: Image
search research</span><br>
<!-- Make sure you modify the date of the 4Cast in this section -->
<span style="font-size: 11px; font-weight: normal;
color: rgb(102, 102, 102); font-style: italic;
font-family: arial;">December 3rd, 2014</span></p>
<!-- Begin copy of Web Source here -->
<p style="text-align: justify;font-size: 16px;
font-family: arial; line-height: 110%;"><img
src="cid:part4.05050509.01060005@oplin.org"
alt="search icon" align="left" height="105"
width="100">How many times have you had a
library patron say, "I once read a really good
book, it had a red cover with a bicycle on the
front [or some other cover description] - can you
find that for me again?" That kind of request to
basically find a described image (the book cover)
doesn't just happen in libraries anymore. As the
content of the Internet continues to shift from
text to graphics, accurately searching for images
based on a general description becomes more and
more important to some of the biggest Internet
companies. In the past couple of weeks,
researchers at both Google and Yahoo (owner of
Flickr) have posted some interesting news about
their recent work to improve image searching.
</p>
<div> </div>
<ul style="text-align: left;">
<li style="text-align: justify; font-size: 16px;
font-family: arial; line-height: 110%;"><a
href="http://googleresearch.blogspot.com/2014/11/a-picture-is-worth-thousand-coherent.html">A
picture is worth a thousand (coherent) words:
Building a natural description of images</a>
(Google Research Blog | Oriol Vinyals, Alexander
Toshev, Samy Bengio, and Dumitru Erhan) "But
accurately describing a complex scene requires a
deeper representation of what's going on in the
scene, capturing how the various objects relate
to one another and translating it all into
natural-sounding language. Many efforts to
construct computer-generated natural
descriptions of images propose combining current
state-of-the-art techniques in both <a
href="http://en.wikipedia.org/wiki/Computer_vision">computer
vision</a> and <a
href="http://en.wikipedia.org/wiki/Natural_language_processing">natural
language processing</a> to form a <a
href="https://www.cs.cmu.edu/%7Eafarhadi/papers/sentence.pdf">complete
image description approach</a>. But what if we
instead merged recent computer vision and
language models into a single jointly trained
system, taking an image and directly producing a
human readable sequence of words to describe
it?"</li>
<li style="text-align: justify; font-size: 16px;
font-family: arial; line-height: 110%;"><a
href="http://www.eweek.com/cloud/image-search-analysis-emerge-as-powerful-tools-privacy-threat-2.html">Image
search, analysis emerge as powerful tools,
privacy threat</a> (eWeek | Mike Elgan) "In a
nutshell, these systems identify objects in a
photograph-say, a boy, a dog, a ball, a tree, a
park, a bird, some clouds and so on-then use
sophisticated artificial intelligence to
understand that the boy is throwing the ball for
the dog to chase in a park and that the bird
isn't involved in the main action of the photo.
Combine this technology with face recognition
and anyone with access (which will be everyone)
will be able to search the Web for people doing
things or involved with or associated with some
activity."</li>
<li style="text-align: justify; font-size: 16px;
font-family: arial; line-height: 110%;"><a
href="http://yahoolabs.tumblr.com/post/103469857701/science-powering-product-yahoo-weather">Science
powering product: Yahoo Weather</a> (Yahoo
Labs | David A. Shamma, Jia Li, Lyndon Kennedy,
and Bart Thomée) "But even more difficult than
finding a stunning photo that accurately
reflects the weather in a given location is the
challenge of finding what the Flickr community
believes is an interesting weather photo. A
little while before we set out to surface our
one million photos, we made an observation about
how people designate photos on Flickr as
'favorites.' Something as simple as favorites
and likes on social network sites are rich
social signals that can be used to surface
themes of images."</li>
<li style="text-align: justify; font-size: 16px;
font-family: arial; line-height: 110%;"><a
href="http://arstechnica.com/business/2014/11/finding-an-image-with-an-image-and-other-feats-of-computer-vision/">Finding
an image with an image and other feats of
computer vision</a> (Ars Technica | Megan
Geuss) "Yahoo's efforts to make photo search
better has a simple mantra: 'more relevant
photos for users, not just the most popular
photos,' as Li put it. To that extent, Flickr
tries to improve general search while also
improving search relevance within a person's
likely-massive online photo album. Shamma noted
that batch upload and the gigabytes and
terabytes of storage offered to customers at
relatively cheap prices have changed how we
photograph things. Accordingly, storage and
recall of photographs has to adapt to fit the
morphing definition of photography. 'The
practice of photography is changing very
quickly, using photos for communication has been
growing,' Shamma said."</li>
</ul>
<div style="text-align: left;"> </div>
<p style="text-align: left; font-size: 20px;
font-family: arial; line-height: 110%;"><small><strong><em>Articles
from <a href="http://ohioweblibrary.org">Ohio
Web Library</a>:</em></strong></small><br>
</p>
<div style="text-align: justify; font-size: 16px;
font-family: arial; line-height: 110%;">
<ul>
<li><a
href="http://web.a.ebscohost.com.proxy.oplin.org/chc/detail?sid=4526ea1f-cbdc-4b82-8091-5653d181d008%40sessionmgr4001&vid=0&hid=4106&bdata=JnNpdGU9Y2hjLWxpdmU%3d#db=cmh&AN=86149983">Leveraging
multimedia in web search.</a> (<em>Online
Searcher</em>, March/April 2013, p62-64 |
Greg R. Notess)</li>
<li><a
href="http://web.a.ebscohost.com.proxy.oplin.org/lrc/detail/detail?sid=a99c1848-0729-4bc6-8ece-8b1c8c1f2732%40sessionmgr4003&vid=0&hid=4106&bdata=JnNpdGU9bHJjLWxpdmU%3d#db=lfh&AN=25902122">Getting
the picture.</a> (<em>European Journal of
English Studies</em>, Aug. 2007, p193-206 |
Julia Thomas)</li>
<li><a
href="http://web.a.ebscohost.com.proxy.oplin.org/ehost/detail/detail?sid=c1fb0d11-4c1c-4536-88b4-31ce07ab5bff%40sessionmgr4004&vid=0&hid=4106&bdata=JnNpdGU9ZWhvc3QtbGl2ZQ%3d%3d#db=aph&AN=74267899">Finding
images in an online public access catalogue:
Analysis of user queries, subject headings,
and description notes.</a> (<em>Canadian
Journal of Information & Library
Sciences</em>, Sept. 2010, p271-295 |
Youngok Choi and Ingrid Hsieh-Yee)</li>
</ul>
</div>
<div style="text-align: left;"> </div>
<!-- End paste of web source here --> </td>
</tr>
<tr>
<td style="" solid="" background-color:="" rgb(255,=""
255,="" 255);="" >=""
background="http://www.oplin.org/4cast/wp-content/themes/4cast/images/kubrickbgwide.jpg"
valign="top" width="760"><span style="font-size:
10px; color: rgb(96, 96, 96); line-height: 100%;
font-family: verdana;">
<hr><!-- Begin standard subscription verbiage -->
<div style="text-align: justify;">The <strong><em>OPLIN
4cast</em></strong>
is a weekly compilation of
recent headlines, topics, and trends that could
impact public
libraries. You can subscribe to it in a variety
of ways, such as: <br>
</div>
<div style="text-align: left;"> </div>
<ul>
<li style="text-align: justify;"><strong>RSS
feed.</strong>
You
can receive the OPLIN 4cast
via RSS feed by subscribing to the following
URL:
<a class="moz-txt-link-freetext" href="http://www.oplin.org/4cast/index.php/?feed=rss2">http://www.oplin.org/4cast/index.php/?feed=rss2</a>.
</li>
<li style="text-align: justify;"><strong>Live
Bookmark.</strong>
If you're using the Firefox
web browser, you can go to the 4cast website
(<a class="moz-txt-link-freetext" href="http://www.oplin.org/4cast/">http://www.oplin.org/4cast/</a>) and click on the
orange "radio wave" icon
on the right side of the address bar. In
Internet Explorer 7, click on
the same icon to view or subscribe to the
4cast RSS feed. </li>
<li style="text-align: justify;"><strong>E-mail.</strong>
You
can have the OPLIN 4cast
delivered via e-mail (a'la OPLINlist and
OPLINtech) by subscribing to
the 4cast mailing list at
<a class="moz-txt-link-freetext" href="http://mail.oplin.org/mailman/listinfo/OPLIN4cast">http://mail.oplin.org/mailman/listinfo/OPLIN4cast</a>.
</li>
</ul>
</span> </td>
</tr>
<tr>
<td style="border-top: 0px solid rgb(255, 255, 255);
background-color: rgb(255, 255, 204);"
background="http://www.oplin.org/4cast/wp-content/themes/4cast/images/kubrickfooter.jpg"
valign="top" width="760"> <br>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
<small>
<title>OPLIN 4Cast</title>
<style>
.headerTop { background-color:#FFFFFF; border-top:0px solid #000000; border-bottom:1px solid #FFFFFF; text-align:center; }
.adminText { font-size:16px; color:#0000FF; line-height:200%; font-family:verdana; text-decoration:none; }
.headerBar { background-color:#FFFFFF; border-top:0px solid #333333; border-bottom:0px solid #FFFFFF; }
.title { font-size:20px; font-weight:bold; color:#000000; font-family:arial; line-height:110%; }
.subTitle { font-size:11px; font-weight:normal; color:#000000; font-style:italic; font-family:arial; }
.defaultText { font-size:12px; color:#000000; line-height:150%; font-family:trebuchet ms; }
.footerRow { background-color:#FFFFCC; border-top:0px solid #FFFFFF; }
.footerText { font-size:10px; color:#996600; line-height:100%; font-family:verdana; }
a { color:#0000FF; color:#0000FF; color:#0000FF; }
</style>
</small>
</body>
</html>