<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Does ippiMatchTemplate able to get subpixel accuracy? in Intel® Integrated Performance Primitives</title>
    <link>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983097#M21507</link>
    <description>Hi there,&lt;BR /&gt;   I wonder that whether ippiMatchTemplate could reach subpixel accuracy?&lt;BR /&gt;   Thx</description>
    <pubDate>Wed, 27 Jul 2005 04:12:11 GMT</pubDate>
    <dc:creator>shenganx</dc:creator>
    <dc:date>2005-07-27T04:12:11Z</dc:date>
    <item>
      <title>Does ippiMatchTemplate able to get subpixel accuracy?</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983097#M21507</link>
      <description>Hi there,&lt;BR /&gt;   I wonder that whether ippiMatchTemplate could reach subpixel accuracy?&lt;BR /&gt;   Thx</description>
      <pubDate>Wed, 27 Jul 2005 04:12:11 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983097#M21507</guid>
      <dc:creator>shenganx</dc:creator>
      <dc:date>2005-07-27T04:12:11Z</dc:date>
    </item>
    <item>
      <title>Re: Does ippiMatchTemplate able to get subpixel accuracy?</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983098#M21508</link>
      <description>When it is the easiest&lt;BR /&gt;1.I use ippiMatchTemplate_CoeffNormed_8u32f_C1R.&lt;BR /&gt;2.I use the maximum and the four pixels in neighborhood of the result.&lt;BR /&gt;3.I do curve fitting by using it.&lt;BR /&gt;4.I solve the simultaneous equations every x and y.&lt;BR /&gt;&lt;BR /&gt;simultaneous equations&lt;BR /&gt;  MacthValue1 := a * x1^2 + b * x1 + c;&lt;BR /&gt;  MacthValue2 := a * x2^2 + b * x2 + c;&lt;BR /&gt;  MacthValue3 := a * x3^2 + b * x3 + c;&lt;BR /&gt;&lt;BR /&gt;differential&lt;BR /&gt;  0 := 2 * a * x + b;&lt;BR /&gt;&lt;BR /&gt;SubPixel := Peak&lt;BR /&gt;  x := - b / a / 2;&lt;BR /&gt;&lt;BR /&gt;y is also similar.</description>
      <pubDate>Wed, 27 Jul 2005 12:30:38 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983098#M21508</guid>
      <dc:creator>seiji-torigoe</dc:creator>
      <dc:date>2005-07-27T12:30:38Z</dc:date>
    </item>
    <item>
      <title>Re: Does ippiMatchTemplate able to get subpixel accuracy?</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983099#M21509</link>
      <description>Hi, thank you for your reply.&lt;BR /&gt;    I did use this simple approach to intropolate the subpixel accuracy. but I do not think there is lot of proof of that. Why use polynomal why not Gaussian? &lt;BR /&gt;    Thx</description>
      <pubDate>Wed, 27 Jul 2005 20:22:11 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983099#M21509</guid>
      <dc:creator>shenganx</dc:creator>
      <dc:date>2005-07-27T20:22:11Z</dc:date>
    </item>
    <item>
      <title>Re: Does ippiMatchTemplate able to get subpixel accuracy?</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983100#M21510</link>
      <description>When I use the value of three pixels to calculate,&lt;BR /&gt; the Gaussian function obtains the same result.&lt;BR /&gt;The Gaussian function can be transformed into the same type.&lt;BR /&gt; ln(MatchValue) := a * x^2 + b * x + c;</description>
      <pubDate>Thu, 28 Jul 2005 07:23:08 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983100#M21510</guid>
      <dc:creator>seiji-torigoe</dc:creator>
      <dc:date>2005-07-28T07:23:08Z</dc:date>
    </item>
    <item>
      <title>Re: Does ippiMatchTemplate able to get subpixel accuracy?</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983101#M21511</link>
      <description>Hi thank you very much.&lt;BR /&gt;   I can not post plot here, the problem I met is the correlation result jittering beteween two pixels, so I assume the correct correlation result should be in the middle and that is why I want subpixel accuracy. The polynomial interpertation approach I tried. If you looked at my matlab plot, the interpertation results also jittering between two values and the shape of the     subpixel result is identical to the orginal one. they just have a small offset. SO that is why I wander whether this approach is good enough.&lt;BR /&gt;   Thank you again for you kind help.</description>
      <pubDate>Thu, 28 Jul 2005 20:27:29 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983101#M21511</guid>
      <dc:creator>shenganx</dc:creator>
      <dc:date>2005-07-28T20:27:29Z</dc:date>
    </item>
    <item>
      <title>Re: Does ippiMatchTemplate able to get subpixel accuracy?</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983102#M21512</link>
      <description>I think,&lt;BR /&gt;When the image is symmetry, there is no offset.</description>
      <pubDate>Fri, 29 Jul 2005 07:17:50 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Does-ippiMatchTemplate-able-to-get-subpixel-accuracy/m-p/983102#M21512</guid>
      <dc:creator>seiji-torigoe</dc:creator>
      <dc:date>2005-07-29T07:17:50Z</dc:date>
    </item>
  </channel>
</rss>

