Search (3 results, page 1 of 1)

  • × author_ss:"Sievert, M.C."
  • × language_ss:"e"
  • × year_i:[1990 TO 2000}
  1. Sievert, M.C.; Andrews, M.J.: Indexing consistency in Information Science Abstracts (1991) 0.02 
    0.02144916 = product of:
  0.064347476 = sum of:
    0.064347476 = product of:
      0.12869495 = sum of:
        0.12869495 = weight(_text_:indexing in 5655) [ClassicSimilarity], result of:
          0.12869495 = score(doc=5655,freq=2.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.6766778 = fieldWeight in 5655, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.125 = fieldNorm(doc=5655)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)
  2. Patrick, T.B.; Sievert, M.C.; Popescu, M.: Text indexing of images based on graphical image content (1999) 0.02 
    0.016418591 = product of:
  0.049255773 = sum of:
    0.049255773 = product of:
      0.09851155 = sum of:
        0.09851155 = weight(_text_:indexing in 6680) [ClassicSimilarity], result of:
          0.09851155 = score(doc=6680,freq=12.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.51797354 = fieldWeight in 6680, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.0390625 = fieldNorm(doc=6680)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)
    Abstract
    Typically, three alternatives methods are proposed for indexing images in an image database: (1) manually assigning index terms to the image; (2) indexing the images based on associated text; or (3) indexing images based on their graphical content. Method (1) is very labor intensive and intractable for large image databases. Associated text is not always available for method (2). Method (3) may not be sufficiently user- friendly in that users may prefer to express concepts and request information using language rather than images. We describe our investigation of an indexing method that is an alternative to (1) - (3). The method addresses the problem of automatically text indexing images by assigning text index terms to prototypical reference images and using a content based strategy to retrieve images that are similar in graphical content to the reference images. The index terms assigned to the reference images are assigned to the retrieved images using the retrieval similarity scores as term weights. We conclude by discussing reasons why it may be difficult to assign correctly a set of terms rather than a single term
  3. Connaway, L.S.; Sievert, M.C.: Comparison of three classification systems for information on health insurance (1996) 0.01 
    0.008975455 = product of:
  0.026926363 = sum of:
    0.026926363 = product of:
      0.053852726 = sum of:
        0.053852726 = weight(_text_:22 in 7242) [ClassicSimilarity], result of:
          0.053852726 = score(doc=7242,freq=2.0), product of:
            0.17398734 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.049684696 = queryNorm
            0.30952093 = fieldWeight in 7242, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.0625 = fieldNorm(doc=7242)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)
    Date
    22. 4.1997 21:10:19

Authors