<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Jürgen Vogel</style></author><author><style face="normal" font="default" size="100%">Wolf-Tilo Balke</style></author><author><style face="normal" font="default" size="100%">Werner Kießling</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">(Semi-) Automatic Segmentation in Historic Collections of Heraldic Images</style></title><secondary-title><style face="normal" font="default" size="100%">15th International Conference on Pattern recognition (ICPR 2000)</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2000</style></year></dates><urls><related-urls><url><style face="normal" font="default" size="100%">http://www.ifis.cs.tu-bs.de/sites/default/files/biblio/icpr00_pdf_17496.pdf</style></url></related-urls></urls><pub-location><style face="normal" font="default" size="100%">Barcelona, Spain</style></pub-location><abstract><style face="normal" font="default" size="100%">A modern approach to manage multimedia databases is content-based retrieval. Especially in image databases graphical features like color, texture or shape can be used efficiently instead of expensive manual annotations. Due to the large number of image archives and the enormous costs of annotations it is most important to extract adequate features automatically by means of digital image processing. Using the image processing tool MVTec Halcon we propose a preprocessing for heraldic image segmentation that can automatically derive color information from monochrome images as well as semiautomatically segment heraldic bearings. We claim that exploiting application semantics leads to successful image segmentation in digital libraries.</style></abstract></record></records></xml>