14.01.2014 Views

Segmentation of heterogeneous document images : an ... - Tel

Segmentation of heterogeneous document images : an ... - Tel

Segmentation of heterogeneous document images : an ... - Tel

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

tel-00912566, version 1 - 2 Dec 2013<br />

Figure 4.13: This figure displays two types <strong>of</strong> error that frequently occur in the<br />

results <strong>of</strong> text region detection. They happen when there are gaps between words. If<br />

the gap is located in the middle <strong>of</strong> the text region, it appears as holes A <strong>an</strong>d if it exists<br />

near the border <strong>of</strong> the text region, it causes penetrations B. Both problems c<strong>an</strong> be<br />

fixed in the post-processing stage.<br />

Figure 4.14: This figure displays a serious problem when the title <strong>of</strong> the page divides<br />

into two isolated text regions. Currently there is no fix for his problem <strong>an</strong>d the use <strong>of</strong><br />

morphological opening is not recommended to solve it.<br />

82

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!