⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 ltusegmentmap.html

📁 显著区域检测。求的图像中感兴趣区域的位置
💻 HTML
字号:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"                "http://www.w3.org/TR/REC-html40/loose.dtd"><html><head>  <title>Description of LTUsegmentMap</title>  <meta name="keywords" content="LTUsegmentMap">  <meta name="description" content="LTUsegmentMap - segment map using a network of linear threshold units.">  <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">  <meta name="generator" content="m2html &copy; 2003 Guillaume Flandin">  <meta name="robots" content="index, follow">  <link type="text/css" rel="stylesheet" href="../m2html.css"></head><body><a name="_top"></a><div><a href="../index.html">Home</a> &gt;  <a href="#">mfiles</a> &gt; LTUsegmentMap.m</div><!--<table width="100%"><tr><td align="left"><a href="../index.html"><img alt="<" border="0" src="../left.png">&nbsp;Master index</a></td><td align="right"><a href="index.html">Index for .\mfiles&nbsp;<img alt=">" border="0" src="../right.png"></a></td></tr></table>--><h1>LTUsegmentMap</h1><h2><a name="_name"></a>PURPOSE <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2><div class="box"><strong>LTUsegmentMap - segment map using a network of linear threshold units.</strong></div><h2><a name="_synopsis"></a>SYNOPSIS <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2><div class="box"><strong>function [resultMap,segMaps] = LTUsegmentMap(map,seedPoint,varargin) </strong></div><h2><a name="_description"></a>DESCRIPTION <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2><div class="fragment"><pre class="comment"> LTUsegmentMap - segment map using a network of linear threshold units. [resultMap,segMaps] = LTUsegmentMap(map,seedPoint)    Segment the map around the seedPoint using a network of linear    threshold units. Returns a binary map in resultMap and the     intermediate maps at each time step in segMaps.    This function is A LOT slower than fastSegmentMap!     (But it works with model neurons.)    See section 3 of this paper for details:      Walther, D., and Koch, C. (2006). Modeling attention to salient       proto-objects. Neural Networks 19, pp. 1395-1407. [resultMap,segMaps] = LTUsegmentMap(map,seedPoint,thresh)    Use threshold thresh for segmentation (default: 0.1).    This threshold is relative to the map activity at    the seedPoint, i.e. the actual threshold is thresh * map(seedPoint). See also <a href="makeLTUsegmentNetwork.html" class="code" title="function LTUnetwork = makeLTUsegmentNetwork(mapSize,thresh)">makeLTUsegmentNetwork</a>, <a href="LTUsimulate.html" class="code" title="function [output,newStates] = LTUsimulate(LTUnetwork,states,inputs,numIter)">LTUsimulate</a>, <a href="fastSegmentMap.html" class="code" title="function resultMap = fastSegmentMap(map,seedPoint,varargin)">fastSegmentMap</a>, <a href="estimateShape.html" class="code" title="function shapeData = estimateShape(salmap,saliencyData,winner,params)">estimateShape</a>, <a href="dataStructures.html" class="code" title="">dataStructures</a>.</pre></div><!-- crossreference --><h2><a name="_cross"></a>CROSS-REFERENCE INFORMATION <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2>This function calls:<ul style="list-style-image:url(../matlabicon.gif)"><li><a href="LTUsimulate.html" class="code" title="function [output,newStates] = LTUsimulate(LTUnetwork,states,inputs,numIter)">LTUsimulate</a>	LTUsimulate - simulates an LTU network for numIter time steps.</li><li><a href="makeLTUsegmentNetwork.html" class="code" title="function LTUnetwork = makeLTUsegmentNetwork(mapSize,thresh)">makeLTUsegmentNetwork</a>	makeLTUsegmentNetwork - creates an LTU network for map segmentation.</li><li><a href="timeString.html" class="code" title="function s = timeString()">timeString</a>	timeString returns the current time and date in a convenient string format.</li></ul>This function is called by:<ul style="list-style-image:url(../matlabicon.gif)"><li><a href="estimateShape.html" class="code" title="function shapeData = estimateShape(salmap,saliencyData,winner,params)">estimateShape</a>	estimateShape - estimates the shape of the attended proto-object region.</li></ul><!-- crossreference --><h2><a name="_source"></a>SOURCE CODE <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2><div class="fragment"><pre>0001 <span class="comment">% LTUsegmentMap - segment map using a network of linear threshold units.</span>0002 <span class="comment">%</span>0003 <span class="comment">% [resultMap,segMaps] = LTUsegmentMap(map,seedPoint)</span>0004 <span class="comment">%    Segment the map around the seedPoint using a network of linear</span>0005 <span class="comment">%    threshold units. Returns a binary map in resultMap and the</span>0006 <span class="comment">%    intermediate maps at each time step in segMaps.</span>0007 <span class="comment">%    This function is A LOT slower than fastSegmentMap!</span>0008 <span class="comment">%    (But it works with model neurons.)</span>0009 <span class="comment">%    See section 3 of this paper for details:</span>0010 <span class="comment">%      Walther, D., and Koch, C. (2006). Modeling attention to salient</span>0011 <span class="comment">%      proto-objects. Neural Networks 19, pp. 1395-1407.</span>0012 <span class="comment">%</span>0013 <span class="comment">% [resultMap,segMaps] = LTUsegmentMap(map,seedPoint,thresh)</span>0014 <span class="comment">%    Use threshold thresh for segmentation (default: 0.1).</span>0015 <span class="comment">%    This threshold is relative to the map activity at</span>0016 <span class="comment">%    the seedPoint, i.e. the actual threshold is thresh * map(seedPoint).</span>0017 <span class="comment">%</span>0018 <span class="comment">% See also makeLTUsegmentNetwork, LTUsimulate, fastSegmentMap, estimateShape, dataStructures.</span>0019   0020 <span class="comment">% This file is part of the SaliencyToolbox - Copyright (C) 2006-2007</span>0021 <span class="comment">% by Dirk B. Walther and the California Institute of Technology.</span>0022 <span class="comment">% See the enclosed LICENSE.TXT document for the license agreement.</span>0023 <span class="comment">% More information about this project is available at:</span>0024 <span class="comment">% http://www.saliencytoolbox.net</span>0025 0026 <a name="_sub0" href="#_subfunctions" class="code">function [resultMap,segMaps] = LTUsegmentMap(map,seedPoint,varargin)</a>0027 0028 <span class="keyword">if</span> isempty(varargin) thresh = 0.1;0029 <span class="keyword">else</span> thresh = varargin{1}; <span class="keyword">end</span>0030 0031 numIter = -1;0032 eps = 0.001;0033 0034 <span class="comment">% prepare data structures for the result</span>0035 imSize = size(map.data);0036 lab = map.label;0037 seedVal = map.data(seedPoint(1),seedPoint(2));0038 <span class="keyword">if</span> (seedVal &lt; eps)0039   resultMap.origImage = map.origImage;0040   resultMap.label = [<span class="string">'seg-0: '</span> lab];0041   resultMap.data = zeros(imSize);0042   resultMap.date = <a href="timeString.html" class="code" title="function s = timeString()">timeString</a>;0043   resultMap.parameters = map.parameters;0044   segMaps = [];0045   <span class="keyword">return</span>;0046 <span class="keyword">end</span>0047 0048 <span class="comment">% create the segmentation network</span>0049 LTUnetwork = <a href="makeLTUsegmentNetwork.html" class="code" title="function LTUnetwork = makeLTUsegmentNetwork(mapSize,thresh)">makeLTUsegmentNetwork</a>(imSize,thresh);0050 select = zeros(imSize);0051 select(seedPoint(1),seedPoint(2)) = 1;0052 input = [map.data(:)/seedVal;select(:)];0053 states = zeros(1,LTUnetwork.numCells);0054 0055 keepgoing = 1;0056 iter = 0;0057 <span class="keyword">while</span> (keepgoing)0058   iter = iter + 1;0059   [output,states] = <a href="LTUsimulate.html" class="code" title="function [output,newStates] = LTUsimulate(LTUnetwork,states,inputs,numIter)">LTUsimulate</a>(LTUnetwork,states,input,2);0060   segMaps(iter).origImage = map.origImage;0061   segMaps(iter).label = sprintf(<span class="string">'seg-%d: %s'</span>,iter,lab);0062   segMaps(iter).data = reshape(output,imSize);0063   segMaps(iter).date = <a href="timeString.html" class="code" title="function s = timeString()">timeString</a>;0064   segMaps(iter).parameters = map.parameters;0065   <span class="keyword">if</span> (numIter &gt; 0)0066     keepgoing = (iter &lt;= numIter);0067   <span class="keyword">else</span>0068     <span class="keyword">if</span> (iter == 1)0069       keepgoing = 1;0070     <span class="keyword">else</span>0071       keepgoing = ~isequal(output,old_output);0072     <span class="keyword">end</span>0073     old_output = output;0074   <span class="keyword">end</span>0075 <span class="keyword">end</span>0076 0077 resultMap = segMaps(end);</pre></div><hr><address>Generated on Fri 07-Sep-2007 14:42:18 by <strong><a href="http://www.artefact.tk/software/matlab/m2html/">m2html</a></strong> &copy; 2003</address></body></html>

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -