<?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 Translation invariant wavelet transforms in Intel® Integrated Performance Primitives</title>
    <link>https://community.intel.com/t5/Intel-Integrated-Performance/Translation-invariant-wavelet-transforms/m-p/832801#M5700</link>
    <description>Hi experts,&lt;BR /&gt; Is there functionality available within IPP to perform translation invariant wavelet transforms (also&lt;BR /&gt;known as non-critically sampled WT)? Alternatively, if someone can advise me on how to&lt;BR /&gt;build one, based on the WT components already available, that would be great too..&lt;BR /&gt;Thanks,&lt;BR /&gt;Sid.</description>
    <pubDate>Fri, 09 Sep 2011 23:06:41 GMT</pubDate>
    <dc:creator>siddy</dc:creator>
    <dc:date>2011-09-09T23:06:41Z</dc:date>
    <item>
      <title>Translation invariant wavelet transforms</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Translation-invariant-wavelet-transforms/m-p/832801#M5700</link>
      <description>Hi experts,&lt;BR /&gt; Is there functionality available within IPP to perform translation invariant wavelet transforms (also&lt;BR /&gt;known as non-critically sampled WT)? Alternatively, if someone can advise me on how to&lt;BR /&gt;build one, based on the WT components already available, that would be great too..&lt;BR /&gt;Thanks,&lt;BR /&gt;Sid.</description>
      <pubDate>Fri, 09 Sep 2011 23:06:41 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Translation-invariant-wavelet-transforms/m-p/832801#M5700</guid>
      <dc:creator>siddy</dc:creator>
      <dc:date>2011-09-09T23:06:41Z</dc:date>
    </item>
    <item>
      <title>Translation invariant wavelet transforms</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Translation-invariant-wavelet-transforms/m-p/832802#M5701</link>
      <description>Hi Sid, &lt;BR /&gt;&lt;BR /&gt;As you see, IPP provide tranditional DWT, see all WT function lists provided by IPP and schematic diagramin IPP manual: &lt;BR /&gt;C:\Program Files (x86)\Intel\ComposerXE-2011\Documentation\en_US\ipp\ipp_manual\index.htm&lt;BR /&gt;and the resampling stepswas capsulated in the function.&lt;BR /&gt;&lt;BR /&gt;Butdo you have exact relationship conversion between invariant wavelet transforms and DWT? if yes, thenyou may consider toimplement one based on the existingWT. &lt;BR /&gt;&lt;BR /&gt;Regards,&lt;BR /&gt;Ying</description>
      <pubDate>Thu, 15 Sep 2011 03:31:33 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Translation-invariant-wavelet-transforms/m-p/832802#M5701</guid>
      <dc:creator>Ying_H_Intel</dc:creator>
      <dc:date>2011-09-15T03:31:33Z</dc:date>
    </item>
    <item>
      <title>Translation invariant wavelet transforms</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Translation-invariant-wavelet-transforms/m-p/832803#M5702</link>
      <description>Hi Ying,&lt;BR /&gt; Thanks for the reply. I must say, I was trying to avoid implementing, but it seems that&lt;BR /&gt;there is no other alternative. non-critically sampled wavelets zero pad the filters before convolution at each level, hence at each scale we get 4 bands of the same size as the original image. A lot of things change because of this, but in the implementational sense, this is the basic difference, and the advantage is that point-to point correspondence is maintained which is beneficial for noise removal applications. &lt;BR /&gt;With this information, maybe you can giude me a bit closer to the existing functionality in IPP for a working&lt;BR /&gt;solution.&lt;BR /&gt;Thanks again, &lt;BR /&gt;sid.</description>
      <pubDate>Thu, 15 Sep 2011 16:26:38 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Translation-invariant-wavelet-transforms/m-p/832803#M5702</guid>
      <dc:creator>siddy</dc:creator>
      <dc:date>2011-09-15T16:26:38Z</dc:date>
    </item>
    <item>
      <title>Translation invariant wavelet transforms</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/Translation-invariant-wavelet-transforms/m-p/832804#M5703</link>
      <description>Hi Sid,&lt;BR /&gt;&lt;BR /&gt;Sorry for missing your reply. &lt;BR /&gt;Here is C codeusing Intel IPP WT. &lt;BR /&gt;&lt;A href="http://software.intel.com/en-us/articles/intel-integrated-performance-primitives-code-samples/"&gt;&lt;B&gt;Code Samples for the Intel Integrated Performance Primitives (Intel IPP) Library 7.0*&lt;/B&gt;&lt;/A&gt;&lt;BR /&gt;w_ipp-samples_p_7.0.7.064\ipp-samples\image-processing\2d-wavelet-transform&lt;BR /&gt;&lt;BR /&gt;as the manual, it require the src is 2xdst. So itseemsnot workable to pad the filters to get same size of original image. &lt;BR /&gt;&lt;BR /&gt;Best Regards,&lt;BR /&gt;Ying</description>
      <pubDate>Mon, 04 Jun 2012 08:17:05 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/Translation-invariant-wavelet-transforms/m-p/832804#M5703</guid>
      <dc:creator>Ying_H_Intel</dc:creator>
      <dc:date>2012-06-04T08:17:05Z</dc:date>
    </item>
  </channel>
</rss>

