Browsing by Subject "Computer assisted"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    An ontology-based universal design knowledge support system
    (Elsevier, 2011-05) Afacan, Yasemin; Demirkan, H.
    An effective and efficient knowledge support system is crucial for universal design process, as it has become a major design issue in the last decade with the growth of the elderly population and disabled people. There are a limited number of CAD investigations on the nature of knowledge processing that supports the cognitive activities of universal design process. Therefore, this paper proposes an ontology-based computer-assisted universal design (CAUD) plug-in tool that supports designers in developing satisfactory universal design solutions in the conceptual design phase. The required knowledge processing and representation of the developed tool is motivated by the ontological language. It is based on the multiple divergence-convergence cognitive strategies and cognitive needs of designers in the analysis/synthesis/evaluation operations. The CAUD plug-in tool is the first attempt to interface the universal design knowledge ontologically and respond to the requirements of conceptual design phase. According to the user acceptance study, the tool is assessed as useful, understandable, efficient, supportive and satisfactory.
  • Thumbnail Image
    ItemOpen Access
    Segmentation of cervical cell images
    (IEEE, 2010) Kale, A.; Aksoy, S.
    The key step of a computer-assisted screening system that aims early diagnosis of cervical cancer is the accurate segmentation of cells. In this paper, we propose a two-phase approach to cell segmentation in Pap smear test images with the challenges of inconsistent staining, poor contrast, and overlapping cells. The first phase consists of segmenting an image by a non-parametric hierarchical segmentation algorithm that uses spectral and shape information as well as the gradient information. The second phase aims to obtain nucleus regions and cytoplasm areas by classifying the segments resulting from the first phase based on their spectral and shape features. Experiments using two data sets show that our method performs well for images containing both a single cell and many overlapping cells. © 2010 IEEE.