Segmentation methods have been used extensively in image analysis, automatic industrial classification and defective pieces searching. Starting with the analysis of satellite images, we found that using some windows driven segmentation algorithms with an adequate set of parameters, it was possible to segmentate only specific parts of the images. Taking advantage of this behavior, we developed a wide set of alternative segmentation algorithms. Combining, later, these previous techniques into a composed system that worked with mobile windows. Different alternatives (method, parameters) generate different segmentated images, which reveal different set of objects, requiring different resources. The composition of the different segmentation mechanisms and its later application is done using a knowledge model that integrates previous partial work models. In this paper, it is showed this knowledge model of the segmentation process that integrates a wide set of techniques.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.