<?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 Re: Ippi's example 9-5: Separable kernel convolution in Intel® Integrated Performance Primitives</title>
    <link>https://community.intel.com/t5/Intel-Integrated-Performance/Ippi-s-example-9-5-Separable-kernel-convolution/m-p/873013#M9160</link>
    <description>&lt;BR /&gt;Hi Lior, &lt;BR /&gt;&lt;BR /&gt;In the file attached, the Separable_3x3 function is using duplicate border (ippBorderRepl), while other two filter functions are using 0 border. &lt;BR /&gt;&lt;BR /&gt;I modified somecode to make that sample more easily to understand ( attached). The code can produce the same output for three filter functions. &lt;BR /&gt;&lt;BR /&gt;Thanks,&lt;BR /&gt;Chao</description>
    <pubDate>Tue, 13 Jan 2009 07:43:24 GMT</pubDate>
    <dc:creator>Chao_Y_Intel</dc:creator>
    <dc:date>2009-01-13T07:43:24Z</dc:date>
    <item>
      <title>Ippi's example 9-5: Separable kernel convolution</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Ippi-s-example-9-5-Separable-kernel-convolution/m-p/873009#M9156</link>
      <description>Hi, I can't get example 9-5 in the ippi manual to work. my code is as follow:&lt;BR /&gt;&lt;BR /&gt; Ipp16s img[6*6]= {	0, 0, 0, 0, 0, 0, &lt;BR /&gt; 0, 1, 0,-1, 0, 0,&lt;BR /&gt; 0, 0,-1, 0, 2, 0,&lt;BR /&gt; 0, 1, 0,-2, 1, 0,&lt;BR /&gt; 0, 1, 1, 0, 0, 0,&lt;BR /&gt; 0, 0, 0, 0, 0, 0 };&lt;BR /&gt; &lt;BR /&gt;Ipp16s output[4*4];&lt;BR /&gt; Ipp16s buf[4*4];&lt;BR /&gt;Ipp16s kerx[3] = {1, 1, 1};&lt;BR /&gt; Ipp16s kery[3] = {1, 1, 1};&lt;BR /&gt;IppiSize roi = {4,4};&lt;BR /&gt; &lt;BR /&gt;ippiCopy_16s_C1R(img+7, 6*sizeof(Ipp16s), buf, 4*sizeof(Ipp16s), roi);&lt;BR /&gt; Separable_3x3(buf, 4*sizeof(Ipp16s), output, 4*sizeof(Ipp16s), roi, kerx, kery);&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;can anyone help?&lt;BR /&gt;</description>
      <pubDate>Tue, 06 Jan 2009 12:48:22 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Ippi-s-example-9-5-Separable-kernel-convolution/m-p/873009#M9156</guid>
      <dc:creator>liorda</dc:creator>
      <dc:date>2009-01-06T12:48:22Z</dc:date>
    </item>
    <item>
      <title>Re: Ippi's example 9-5: Separable kernel convolution</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Ippi-s-example-9-5-Separable-kernel-convolution/m-p/873010#M9157</link>
      <description>&lt;DIV style="margin:0px;"&gt;&lt;BR /&gt;&lt;BR /&gt;Hello, &lt;BR /&gt;&lt;BR /&gt;This looks an image border issue. Image filtering functions assume that for each pixel being processed, adjacent pixels also exist. You may check the following artile for more information on this topic:&lt;BR /&gt;&lt;A href="http://software.intel.com/en-us/articles/intel-integrated-performance-primitives-intel-ipp-processing-an-image-from-edge-to-edge" target="_blank"&gt;http://software.intel.com/en-us/articles/intel-integrated-performance-primitives-intel-ipp-processing-an-image-from-edge-to-edge&lt;/A&gt;.&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;Could you look at if thecode bellow work for u? &lt;BR /&gt;&lt;BR /&gt;Ipp16s img[6*6]= { 0, 0, 0, 0, 0, 0, &lt;BR /&gt;0, 1, 0,-1, 0, 0,&lt;BR /&gt;0, 0,-1, 0, 2, 0,&lt;BR /&gt;0, 1, 0,-2, 1, 0,&lt;BR /&gt;0, 1, 1, 0, 0, 0,&lt;BR /&gt;0, 0, 0, 0, 0, 0 };&lt;BR /&gt;&lt;BR /&gt;Ipp16s output[4*4];&lt;BR /&gt;Ipp16s buf[6*6];&lt;BR /&gt;Ipp16s kerx[3] = {1, 1, 1};&lt;BR /&gt;Ipp16s kery[3] = {1, 1, 1};&lt;BR /&gt;IppiSize roi = {4,4};&lt;BR /&gt;IppiSize roi1 = {6,6};&lt;BR /&gt;&lt;BR /&gt;ippiCopy_16s_C1R(img, 6*sizeof(Ipp16s), buf, 6*sizeof(Ipp16s), roi1);&lt;BR /&gt;Separable_3x3(buf+7, 6*sizeof(Ipp16s), output, 4*sizeof(Ipp16s), roi, kerx, kery);&lt;BR /&gt;&lt;BR /&gt;Thanks,&lt;BR /&gt;Chao&lt;/DIV&gt;
&lt;BR /&gt;</description>
      <pubDate>Thu, 08 Jan 2009 08:18:14 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Ippi-s-example-9-5-Separable-kernel-convolution/m-p/873010#M9157</guid>
      <dc:creator>Chao_Y_Intel</dc:creator>
      <dc:date>2009-01-08T08:18:14Z</dc:date>
    </item>
    <item>
      <title>Re: Ippi's example 9-5: Separable kernel convolution</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Ippi-s-example-9-5-Separable-kernel-convolution/m-p/873011#M9158</link>
      <description>&lt;DIV style="margin:0px;"&gt;
&lt;DIV id="quote_reply" style="width: 100%; margin-top: 5px;"&gt;
&lt;DIV style="margin-left:2px;margin-right:2px;"&gt;Quoting - &lt;A href="https://community.intel.com/en-us/profile/21699"&gt;Chao Yu (Intel)&lt;/A&gt;&lt;/DIV&gt;
&lt;DIV style="background-color:#E5E5E5; padding:5px;border: 1px; border-style: inset;margin-left:2px;margin-right:2px;"&gt;&lt;EM&gt;
&lt;DIV style="margin:0px;"&gt;&lt;BR /&gt;&lt;BR /&gt;Hello, &lt;BR /&gt;&lt;BR /&gt;This looks an image border issue. Image filtering functions assume that for each pixel being processed, adjacent pixels also exist. You may check the following artile for more information on this topic:&lt;BR /&gt;&lt;A href="http://software.intel.com/en-us/articles/intel-integrated-performance-primitives-intel-ipp-processing-an-image-from-edge-to-edge" target="_blank"&gt;http://software.intel.com/en-us/articles/intel-integrated-performance-primitives-intel-ipp-processing-an-image-from-edge-to-edge&lt;/A&gt;.&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;Could you look at if thecode bellow work for u? &lt;BR /&gt;&lt;BR /&gt;Ipp16s img[6*6]= { 0, 0, 0, 0, 0, 0, &lt;BR /&gt;0, 1, 0,-1, 0, 0,&lt;BR /&gt;0, 0,-1, 0, 2, 0,&lt;BR /&gt;0, 1, 0,-2, 1, 0,&lt;BR /&gt;0, 1, 1, 0, 0, 0,&lt;BR /&gt;0, 0, 0, 0, 0, 0 };&lt;BR /&gt;&lt;BR /&gt;Ipp16s output[4*4];&lt;BR /&gt;Ipp16s buf[6*6];&lt;BR /&gt;Ipp16s kerx[3] = {1, 1, 1};&lt;BR /&gt;Ipp16s kery[3] = {1, 1, 1};&lt;BR /&gt;IppiSize roi = {4,4};&lt;BR /&gt;IppiSize roi1 = {6,6};&lt;BR /&gt;&lt;BR /&gt;ippiCopy_16s_C1R(img, 6*sizeof(Ipp16s), buf, 6*sizeof(Ipp16s), roi1);&lt;BR /&gt;Separable_3x3(buf+7, 6*sizeof(Ipp16s), output, 4*sizeof(Ipp16s), roi, kerx, kery);&lt;BR /&gt;&lt;BR /&gt;Thanks,&lt;BR /&gt;Chao&lt;/DIV&gt;
&lt;BR /&gt;&lt;/EM&gt;&lt;/DIV&gt;
&lt;/DIV&gt;
&lt;/DIV&gt;
&lt;BR /&gt;I'm maybe missing something, but I still can't get the code to work as expected. the other convolution methods work normally. the attched example should produce the same output, but the separable method somehow disfunctions...&lt;BR /&gt;&lt;BR /&gt;I'd love to hear what am I doing wrong. my complete test code attached.&lt;BR /&gt;&lt;BR /&gt;Thanks,&lt;BR /&gt;--Lior&lt;BR /&gt;</description>
      <pubDate>Fri, 09 Jan 2009 13:43:15 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Ippi-s-example-9-5-Separable-kernel-convolution/m-p/873011#M9158</guid>
      <dc:creator>liorda</dc:creator>
      <dc:date>2009-01-09T13:43:15Z</dc:date>
    </item>
    <item>
      <title>Re: Ippi's example 9-5: Separable kernel convolution</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Ippi-s-example-9-5-Separable-kernel-convolution/m-p/873012#M9159</link>
      <description>can anyone please have a look? I followd the manual example and I can't get right results.&lt;BR /&gt;&lt;BR /&gt;Thanks,&lt;BR /&gt;--Lior&lt;BR /&gt;</description>
      <pubDate>Sun, 11 Jan 2009 21:29:06 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Ippi-s-example-9-5-Separable-kernel-convolution/m-p/873012#M9159</guid>
      <dc:creator>liorda</dc:creator>
      <dc:date>2009-01-11T21:29:06Z</dc:date>
    </item>
    <item>
      <title>Re: Ippi's example 9-5: Separable kernel convolution</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Ippi-s-example-9-5-Separable-kernel-convolution/m-p/873013#M9160</link>
      <description>&lt;BR /&gt;Hi Lior, &lt;BR /&gt;&lt;BR /&gt;In the file attached, the Separable_3x3 function is using duplicate border (ippBorderRepl), while other two filter functions are using 0 border. &lt;BR /&gt;&lt;BR /&gt;I modified somecode to make that sample more easily to understand ( attached). The code can produce the same output for three filter functions. &lt;BR /&gt;&lt;BR /&gt;Thanks,&lt;BR /&gt;Chao</description>
      <pubDate>Tue, 13 Jan 2009 07:43:24 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Ippi-s-example-9-5-Separable-kernel-convolution/m-p/873013#M9160</guid>
      <dc:creator>Chao_Y_Intel</dc:creator>
      <dc:date>2009-01-13T07:43:24Z</dc:date>
    </item>
  </channel>
</rss>

