Sophie

Sophie

distrib > Mandriva > 2010.0 > i586 > media > contrib-release > by-pkgid > 4a71d9984febeb5a206904a5a379841a > files > 627

python-morph-0.8-7mdv2010.0.noarch.rpm

<html>
  <head>
    <meta content="text/html; charset=ISO-8859-1" http-equiv="Content-Type">
    <title>mmdlabeltext</title>
    <link href="../tbxdok.css" rel="stylesheet">
  </head>
  <body>
    <table class="topNav">
      <tr>
        <td class="index">
                  [<a href="../mmdemos/mmdasp.html"><tt>mmdasp</tt></a>]
              
                  [<a href="index.html">Up</a>]
                  
                  [<a href="../mmdemos/mmdbeef.html"><tt>mmdbeef</tt></a>]
              </td>
        <td class="title">Demonstrations</td>
      </tr>
    </table>
    <h1>mmdlabeltext
      <br>
      <span class="subtitle">Segmenting letters, words and paragraphs.
</span>
    </h1>
    <div class="descr">
      <H2>Description</H2>
      <div class="H2">
        <p>
                      In this example, a digitized text is processed to identify the letters, words and paragraphs. This demonstration uses only the 
          <span class="fun">mmlabel</span> function with different connectivity parameters.
                  
        </p>
      </div>
    </div>
    <div class="script">
      <H2>Demo Script</H2>
      <div class="H2">
        <div class="slide">
          <H3>Reading</H3>
          <div class="H3">
            <p>
              <p>
                        The text image is read.
                    
              </p>
              <div class="example">
                <div class="listing">
                  <pre class="user">&gt;&gt;&gt; f = mmreadgray('stext.tif')</pre>
                  <pre class="computer"></pre>
                  <pre class="user">&gt;&gt;&gt; mmshow(f)</pre>
                  <pre class="computer"></pre>
                </div>
                <table class="images">
                  <tbody align="center">
                    <tr class="image" valign="bottom">
                      <td><img width="320" src="../images/img_mmdlabeltext_001.jpg"></td>
                      <td class="spare"></td>
                    </tr>
                    <tr class="title" valign="baseline">
                      <td><a href="../images/img_mmdlabeltext_001.jpg">f</a></td>
                      <td class="spare"></td>
                    </tr>
                  </tbody>
                </table>
              </div>
            </p>
          </div>
        </div>
        <div class="slide">
          <H3>First, label the letters.</H3>
          <div class="H3">
            <p>
              <p>
                        The letters are the main connected components in the image. So we use the classical 8-connectivity criteria for identify each letter.
                    
              </p>
              <div class="example">
                <div class="listing">
                  <pre class="user">&gt;&gt;&gt; fl=mmlabel(f,mmsebox())</pre>
                  <pre class="computer"></pre>
                  <pre class="user">&gt;&gt;&gt; mmlblshow(fl)</pre>
                  <pre class="computer"></pre>
                </div>
                <table class="images">
                  <tbody align="center">
                    <tr class="image" valign="bottom">
                      <td><img width="320" src="../images/img_mmdlabeltext_002.jpg"></td>
                      <td class="spare"></td>
                    </tr>
                    <tr class="title" valign="baseline">
                      <td><a href="../images/img_mmdlabeltext_002.jpg">fl</a></td>
                      <td class="spare"></td>
                    </tr>
                  </tbody>
                </table>
              </div>
            </p>
          </div>
        </div>
        <div class="slide">
          <H3>Second, label the words.</H3>
          <div class="H3">
            <p>
              <p>
                        The words are made of closed letters. In this case we use a connectivity specified by a rectangle structuring element of 7 pixels high and 11 pixels width, so any two pixels that can be hit by this rectangle, belong to the same connected component. The values 7 and 11 were chosen experimentally and depend on the font size.
                    
              </p>
              <div class="example">
                <div class="listing">
                  <pre class="user">&gt;&gt;&gt; from Numeric import ones</pre>
                  <pre class="computer"></pre>
                  <pre class="user">&gt;&gt;&gt; sew = mmimg2se(mmbinary(ones((7,11))))</pre>
                  <pre class="computer"></pre>
                  <pre class="user">&gt;&gt;&gt; mmseshow(sew)</pre>
                  <pre class="computer">array([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
       [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
       [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
       [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
       [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
       [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
       [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]],'1')</pre>
                  <pre class="user">&gt;&gt;&gt; fw=mmlabel(f,sew)</pre>
                  <pre class="computer"></pre>
                  <pre class="user">&gt;&gt;&gt; mmlblshow(fw)</pre>
                  <pre class="computer"></pre>
                </div>
                <table class="images">
                  <tbody align="center">
                    <tr class="image" valign="bottom">
                      <td><img width="320" src="../images/img_mmdlabeltext_003.jpg"></td>
                      <td class="spare"></td>
                    </tr>
                    <tr class="title" valign="baseline">
                      <td><a href="../images/img_mmdlabeltext_003.jpg">fw</a></td>
                      <td class="spare"></td>
                    </tr>
                  </tbody>
                </table>
              </div>
            </p>
          </div>
        </div>
        <div class="slide">
          <H3>Finally, label the paragraphs.</H3>
          <div class="H3">
            <p>
              <p>
                        Similarly, paragraphs are closed words. In this case the connectivity is given by a rectangle of 35 by 20 pixels.
                    
              </p>
              <div class="example">
                <div class="listing">
                  <pre class="user">&gt;&gt;&gt; sep = mmimg2se(mmbinary(ones((20,35))))</pre>
                  <pre class="computer"></pre>
                  <pre class="user">&gt;&gt;&gt; fp=mmlabel(f,sep)</pre>
                  <pre class="computer"></pre>
                  <pre class="user">&gt;&gt;&gt; mmlblshow(fp)</pre>
                  <pre class="computer"></pre>
                </div>
                <table class="images">
                  <tbody align="center">
                    <tr class="image" valign="bottom">
                      <td><img width="320" src="../images/img_mmdlabeltext_004.jpg"></td>
                      <td class="spare"></td>
                    </tr>
                    <tr class="title" valign="baseline">
                      <td><a href="../images/img_mmdlabeltext_004.jpg">fp</a></td>
                      <td class="spare"></td>
                    </tr>
                  </tbody>
                </table>
              </div>
            </p>
          </div>
        </div>
      </div>
    </div>
    <div class="seealso">
      <H2>See also</H2>
      <div class="H2">
        <table class="deflist">
          <tbody valign="baseline">
            <tr>
              <td class="term"><a href="../morph/mmlabel.html">mmlabel</a></td>
              <td class="def">Label a binary image.</td>
            </tr>
          </tbody>
        </table>
      </div>
    </div>
    <center>
      <table class="botNav">
        <tr>
          <td class="index">
                    [<a href="../mmdemos/mmdasp.html"><tt>mmdasp</tt></a>]
                
                    [<a href="index.html">Up</a>]
                    
                    [<a href="../mmdemos/mmdbeef.html"><tt>mmdbeef</tt></a>]
                </td>
          <td rowspan="2" class="xhtml"><a href="http://www.python.org"><img width="55" alt="Python" height="22" src="../PythonPoweredSmall.gif"></a></td>
        </tr>
        <tr>
          <td class="copyright">Copyright (c) 2003, Roberto A. Lotufo, UNICAMP-University of Campinas; Rubens C. Machado, CenPRA-Renato Archer Research Center.</td>
        </tr>
      </table>
    </center>
  </body>
</html>