<?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 Contrast measurement in Intel® Integrated Performance Primitives</title>
    <link>https://community.intel.com/t5/Intel-Integrated-Performance/Contrast-measurement/m-p/988606#M22056</link>
    <description>Hi people,&lt;BR /&gt;I am trying to measure for images. I am referring to this paper(http://diuf.unifr.ch/courses03-04/imaging/simoncelli.pdf). &lt;BR /&gt;The paper suggest that i find luminance first and then i find contrast.&lt;BR /&gt;The paper says that luminance could be found by calculating mean intensity.(image is considered as signal).&lt;BR /&gt;And then finally contrast could be found by reomving the mean intensity from the signal. &lt;BR /&gt; And using the standard deviation (the square root of variance) as an estimate of the signal contrast. An unbiased estimate in discrete&lt;BR /&gt;form is given by formula.&lt;BR /&gt;&lt;BR /&gt;My question are&lt;BR /&gt;1. Can i find log average luminance value to calculate luminance&lt;BR /&gt;2. How do represent the image in terms of signal to do the calculation.&lt;BR /&gt;Any suggestions?&lt;BR /&gt;thanks&lt;BR /&gt;Jay</description>
    <pubDate>Thu, 16 Jun 2005 14:30:25 GMT</pubDate>
    <dc:creator>sunderam08</dc:creator>
    <dc:date>2005-06-16T14:30:25Z</dc:date>
    <item>
      <title>Contrast measurement</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Contrast-measurement/m-p/988606#M22056</link>
      <description>Hi people,&lt;BR /&gt;I am trying to measure for images. I am referring to this paper(http://diuf.unifr.ch/courses03-04/imaging/simoncelli.pdf). &lt;BR /&gt;The paper suggest that i find luminance first and then i find contrast.&lt;BR /&gt;The paper says that luminance could be found by calculating mean intensity.(image is considered as signal).&lt;BR /&gt;And then finally contrast could be found by reomving the mean intensity from the signal. &lt;BR /&gt; And using the standard deviation (the square root of variance) as an estimate of the signal contrast. An unbiased estimate in discrete&lt;BR /&gt;form is given by formula.&lt;BR /&gt;&lt;BR /&gt;My question are&lt;BR /&gt;1. Can i find log average luminance value to calculate luminance&lt;BR /&gt;2. How do represent the image in terms of signal to do the calculation.&lt;BR /&gt;Any suggestions?&lt;BR /&gt;thanks&lt;BR /&gt;Jay</description>
      <pubDate>Thu, 16 Jun 2005 14:30:25 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Contrast-measurement/m-p/988606#M22056</guid>
      <dc:creator>sunderam08</dc:creator>
      <dc:date>2005-06-16T14:30:25Z</dc:date>
    </item>
    <item>
      <title>Re: Contrast measurement</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Contrast-measurement/m-p/988607#M22057</link>
      <description>&lt;DIV&gt;&lt;FONT color="#000080" size="2"&gt;
&lt;P&gt;Hi,&lt;/P&gt;
&lt;P&gt;There is no need to do (2)  all necessary functions present in ippIP domain.&lt;/P&gt;
&lt;P&gt;1) mean removal:&lt;/P&gt;&lt;/FONT&gt;&lt;FONT face="Courier New CYR" color="#000080" size="2"&gt;
&lt;P&gt;ippiMean_32f_C1R( pSrc, srcStep, RoiSize, &amp;amp;Mean64f, ippAlgHintAccurate );&lt;/P&gt;
&lt;P&gt;Mean32f = (Ipp32f)Mean64f;&lt;/P&gt;
&lt;P&gt;ippiSubC_32f_C1IR( Mean32f, pSrc, srcStep, RoiSize );&lt;/P&gt;
&lt;P&gt;variance:&lt;/P&gt;
&lt;P&gt;ippiNorm_L2_32f_C1R( pSrc, srcStep, RoiSize, &amp;amp;NormL2, ippAlgHintAccurate );&lt;/P&gt;
&lt;P&gt;Regards,&lt;BR /&gt; Vladimir&lt;/P&gt;&lt;/FONT&gt;&lt;/DIV&gt;</description>
      <pubDate>Wed, 27 Jul 2005 22:35:27 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Contrast-measurement/m-p/988607#M22057</guid>
      <dc:creator>Vladimir_Dudnik</dc:creator>
      <dc:date>2005-07-27T22:35:27Z</dc:date>
    </item>
  </channel>
</rss>

