<?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 Extract lake surface in ArcGIS Spatial Analyst Questions</title>
    <link>https://community.esri.com/t5/arcgis-spatial-analyst-questions/extract-lake-surface/m-p/684724#M10014</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hello. Thank you in advance for any reply!&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I use EVI to help extract water surface of a lake. The result is acceptable but not accurate. I don't want to include the extra small pixel plots when counting the total pixel number of the large lake. How can I erase the "noise" pixels? I've marked "noise" out in the second pic. BTW, this is a raster file and has been reclassified into two categories: 0 for Non-lake, 1 for lake (Blue)&lt;/P&gt;&lt;P&gt;&lt;IMG alt="Capture.PNG" class="image-1 jive-image" src="https://community.esri.com/legacyfs/online/179978_Capture.PNG" style="width: 620px; height: 472px;" /&gt;&lt;/P&gt;&lt;P&gt;&lt;IMG alt="Capture1.png" class="image-2 jive-image" src="https://community.esri.com/legacyfs/online/179979_Capture1.png" style="width: 620px; height: 472px;" /&gt;&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Tue, 09 Feb 2016 20:08:58 GMT</pubDate>
    <dc:creator>Zihan_Lin</dc:creator>
    <dc:date>2016-02-09T20:08:58Z</dc:date>
    <item>
      <title>Extract lake surface</title>
      <link>https://community.esri.com/t5/arcgis-spatial-analyst-questions/extract-lake-surface/m-p/684724#M10014</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hello. Thank you in advance for any reply!&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I use EVI to help extract water surface of a lake. The result is acceptable but not accurate. I don't want to include the extra small pixel plots when counting the total pixel number of the large lake. How can I erase the "noise" pixels? I've marked "noise" out in the second pic. BTW, this is a raster file and has been reclassified into two categories: 0 for Non-lake, 1 for lake (Blue)&lt;/P&gt;&lt;P&gt;&lt;IMG alt="Capture.PNG" class="image-1 jive-image" src="https://community.esri.com/legacyfs/online/179978_Capture.PNG" style="width: 620px; height: 472px;" /&gt;&lt;/P&gt;&lt;P&gt;&lt;IMG alt="Capture1.png" class="image-2 jive-image" src="https://community.esri.com/legacyfs/online/179979_Capture1.png" style="width: 620px; height: 472px;" /&gt;&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Tue, 09 Feb 2016 20:08:58 GMT</pubDate>
      <guid>https://community.esri.com/t5/arcgis-spatial-analyst-questions/extract-lake-surface/m-p/684724#M10014</guid>
      <dc:creator>Zihan_Lin</dc:creator>
      <dc:date>2016-02-09T20:08:58Z</dc:date>
    </item>
    <item>
      <title>Re: Extract lake surface</title>
      <link>https://community.esri.com/t5/arcgis-spatial-analyst-questions/extract-lake-surface/m-p/684725#M10015</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;See &lt;A href="http://pro.arcgis.com/en/pro-app/tool-reference/spatial-analyst/generalization-of-classified-raster-imagery.htm"&gt;this help page&lt;/A&gt;. Start at Identifying Clusters with Region Group. Basically, Region Group, Extract By Attributes (or Con), Nibble.&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Tue, 09 Feb 2016 20:15:24 GMT</pubDate>
      <guid>https://community.esri.com/t5/arcgis-spatial-analyst-questions/extract-lake-surface/m-p/684725#M10015</guid>
      <dc:creator>DarrenWiens2</dc:creator>
      <dc:date>2016-02-09T20:15:24Z</dc:date>
    </item>
    <item>
      <title>Re: Extract lake surface</title>
      <link>https://community.esri.com/t5/arcgis-spatial-analyst-questions/extract-lake-surface/m-p/684726#M10016</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Interesting ... I would agree with Darren, however, unless you have greatly oversimplified what you consider noise, there are some regions that have smaller clusters yet you haven't circled them.&amp;nbsp; Would be fair to say, that you didn't circle all the noise?&amp;nbsp; What about that big lump in the South East corner... is that noise too?&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;So follow Darren's suggestion, perhaps with a focal majority with a moderate sized neighbourhood first to get rid of speckle.&amp;nbsp; Then do the RegionGroup incrementally until you get most of what you call noise identified&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Tue, 09 Feb 2016 21:10:17 GMT</pubDate>
      <guid>https://community.esri.com/t5/arcgis-spatial-analyst-questions/extract-lake-surface/m-p/684726#M10016</guid>
      <dc:creator>DanPatterson_Retired</dc:creator>
      <dc:date>2016-02-09T21:10:17Z</dc:date>
    </item>
  </channel>
</rss>

