<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	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/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Dominion Software, Inc.</title>
	<atom:link href="http://dominionsw.com/wordpress/?feed=rss2" rel="self" type="application/rss+xml" />
	<link>http://dominionsw.com/wordpress</link>
	<description></description>
	<lastBuildDate>Thu, 08 Sep 2011 14:12:40 +0000</lastBuildDate>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3</generator>
		<item>
		<title>2D &#8211; 2D, and 3D-3D Rigid Image Registration &#8211; part 2.</title>
		<link>http://dominionsw.com/wordpress/?p=216</link>
		<comments>http://dominionsw.com/wordpress/?p=216#comments</comments>
		<pubDate>Tue, 05 Jul 2011 02:21:06 +0000</pubDate>
		<dc:creator>admin</dc:creator>
				<category><![CDATA[Uncategorized]]></category>

		<guid isPermaLink="false">http://dominionsw.com/wordpress/?p=216</guid>
		<description><![CDATA[In the previous post we discussed 2D &#8211; 2D  image registration, and in this post we&#8217;ll continue that discussion with 3D &#8211; 3D image registration. I&#8217;d like to again give credit to Dr. Joachim Hornegger&#8217;s online videos, available here, which led me to explore actually implementing these algorithms in Matlab. In the case of 3D -3D Rigid Image registration, we have 2 sets of 3 points located in 3D space though prior measurements. In the case of surgery of the human body, we might have 3 small gold markers, known as &#8220;fiducial markers&#8221; in each 3d image. If our measurements of the marker locations were taken at different times, or with different types of imaging technology, we want to make sure that  we line up the two 3d models as closely as possible, so we can accurately locate the features of interest. Coordinate systems and rotation in 3D Most people are familiar with 3D coordinates as an extension of the 2D Cartesian coordinate system, by adding a Z axis to the X and Y axis. When rotating points in 3D, it is common and intuitive to think of rotating, for instance, 3 degrees about the X axis, -3 degrees about [...]]]></description>
		<wfw:commentRss>http://dominionsw.com/wordpress/?feed=rss2&#038;p=216</wfw:commentRss>
		<slash:comments>0</slash:comments>
<enclosure url="http://dominionsw.com/wordpress/wp-content/uploads/2011/07/3drotation1.mov" length="149840" type="video/quicktime" />
		</item>
		<item>
		<title>2D &#8211; 2D, and 3D-3D Rigid Image Registration &#8211; part 1.</title>
		<link>http://dominionsw.com/wordpress/?p=111</link>
		<comments>http://dominionsw.com/wordpress/?p=111#comments</comments>
		<pubDate>Thu, 02 Jun 2011 00:49:30 +0000</pubDate>
		<dc:creator>admin</dc:creator>
				<category><![CDATA[Uncategorized]]></category>

		<guid isPermaLink="false">http://dominionsw.com/wordpress/?p=111</guid>
		<description><![CDATA[I&#8217;ve recently been watching the online lectures of Dr. Joachim Hornegger&#8217;s Diagnostic Medical Imaging class. For anyone interested in state-of-the-art image processing techniques, especially related to medical imaging, these lectures are extremely useful and also have the side benefit of being entertaining (to geeks, at least). A link to the course website is here. What is Image Registration? Let&#8217;s say that you have 2 pictures of the same object, or scene, taken at different times and also from different angles. If you want to see if anything has changed in the object or scene since the time the first picture was taken, it&#8217;s much easier if the pictures are lined up so that the object is not rotated, or moved up , down, left, or right. In the medical field, perhaps a tumor has changed over time and you want to align two pictures of the tumor in order to more clearly see any changes that might have taken place over time. So we want to align the images, but we don&#8217;t know the angle or shift between the first and second pictures &#8211; and they might have used an x ray device for one image and an MRI for [...]]]></description>
		<wfw:commentRss>http://dominionsw.com/wordpress/?feed=rss2&#038;p=111</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Looking at the edge of Edge Detection – Part 2.</title>
		<link>http://dominionsw.com/wordpress/?p=119</link>
		<comments>http://dominionsw.com/wordpress/?p=119#comments</comments>
		<pubDate>Sun, 25 Jul 2010 17:16:28 +0000</pubDate>
		<dc:creator>admin</dc:creator>
				<category><![CDATA[Uncategorized]]></category>

		<guid isPermaLink="false">http://dominionsw.com/wordpress/?p=119</guid>
		<description><![CDATA[In the first part of this series we discussed first order edge enhancement, and how we looked for changes in the image to determine where an edge was located. To find these changes, we looked at the an approximation of the first derivative &#8211; (the rate of change) &#8211; over sections of the image. We approximated the first derivative with a centered difference equation. We only touched on a few basic concepts, so, there&#8217;s quite a bit more that could be covered on first derivative edge enhancement. There are a number of good books now to explore these concepts &#8211; I&#8217;ll reference them at the end of this post. Let&#8217;s move on to second order edge enhancement. To review, the problem we have at hand is trying to enhance the &#8220;edges&#8221; in an image. When you zoom in on an image on a computer screen, you soon see that the image is actually composed of  pixels &#8211; dots -  it&#8217;s only when we &#8220;stand back&#8221; from the image that we see the image clearly. It&#8217;s a bit like French Impressionist paintings. Too simplify our understanding of the image and how we process it, we can turn our gray image on [...]]]></description>
		<wfw:commentRss>http://dominionsw.com/wordpress/?feed=rss2&#038;p=119</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Angling for Angles</title>
		<link>http://dominionsw.com/wordpress/?p=90</link>
		<comments>http://dominionsw.com/wordpress/?p=90#comments</comments>
		<pubDate>Fri, 23 Jul 2010 02:31:22 +0000</pubDate>
		<dc:creator>admin</dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[Image Processing]]></category>

		<guid isPermaLink="false">http://dominionsw.com/wordpress/?p=90</guid>
		<description><![CDATA[In our previous post, we discussed enhancing edges, sometimes known as &#8220;edge detection&#8221;, although as we said this is a slightly misleading term. In this post we will explore one of the more interesting image processing algorithms for finding the actual edge locations for lines, and their slopes. The algorithm we will explore is the &#8220;Hough Transform&#8221;, and I am always amazed that someone (Paul Hough, for whom it is named) could come up with a method such as this one. In many books it is not thoroughly explained, so I will attempt to really pick it apart in order that you can really get the hang of it. First, recall that a line can be represented by the formula y = mx + b;  Ok, now forget that, because that formula doesn&#8217;t work when the line is vertical &#8211; the slope becomes infinite, and y becomes undefined &#8211; technically known as a singularity. So, what&#8217;s another way to represent a line? Well I will just jump right to the way that the Hough Transform thinks about lines. There are three main parts to this way of representing lines &#8211; first, the point at the origin of the image (0,0). [...]]]></description>
		<wfw:commentRss>http://dominionsw.com/wordpress/?feed=rss2&#038;p=90</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Looking at the edge of Edge Detection – Part 1.</title>
		<link>http://dominionsw.com/wordpress/?p=55</link>
		<comments>http://dominionsw.com/wordpress/?p=55#comments</comments>
		<pubDate>Sun, 11 Jul 2010 22:30:59 +0000</pubDate>
		<dc:creator>admin</dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[Image Processing]]></category>

		<guid isPermaLink="false">http://dominionsw.com/wordpress/?p=55</guid>
		<description><![CDATA[If you’ve done a bit of image processing, or read about it, you’ve probably run into the concept of “edge detection”. In the first part of this article I’ll take a closer look at the basics of edge detection, and explore in more detail what’s going on in those little boxes of numbers. When people hear of the concept  of edge detection in images, they sometimes think of  finding objects in images, and obtaining the actual coordinates of the objects in the image. However, the various algorithms called edge “detection” would  probably better be called edge “enhancement”. These algorithms amplify or mark where the segments in an image change, and the result is a new image showing the location of these changes, which are “edges” in the image. So, the “detection” part does not include creating a map of coordinates of various regions – other algorithms are needed for this task. However, edge detection is a useful tool in preparing images for location detection, and for enhancing the lines, edges, and corners in images for other image processing tasks. If we start with a very simple example, it is easier to understand the basic idea for edge enhancement. Here we [...]]]></description>
		<wfw:commentRss>http://dominionsw.com/wordpress/?feed=rss2&#038;p=55</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>

