<?xml version="1.0" standalone="yes"?>
<Paper uid="T78-1021">
  <Title>The Problem of Naming Shapes: Vision-Language Interface</Title>
  <Section position="4" start_page="159" end_page="159" type="concl">
    <SectionTitle>
4. Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper, we have considered the fol= lowing problems: i. How mueh of analog information is retained during recognition process and at which level the transformation from analog to propositional  takes place? 2. How much of the information stored is procedural (implicit) and structural (explicit) form? 3. What are the primitives for two dimensional and three dimensional shapes? 4. How is the labelling of shapes effected by the  way the shapes are represented?- By studying the shape labels can we hope to learn something about the internal representation of shapes? Clearly, these four questions are intimately related to the general problem: representation of three dimensional objects.</Paragraph>
    <Paragraph position="1"> We are led to the following conclusions. Our conclusions are derived primarily on the basis of our experience in constructing 2-D and 3-D recognition systems and the study of the relevant psycologicaland psycholinguistic literature. i. Analog information is not retained even in a short term memory.</Paragraph>
    <Paragraph position="2"> 2. Our experience and the analysis of the relevant literature leads us to be in favor of the constructuve vision theory. The visual information is represented as structures, with nodes which are either unary or n-ary predicates. The structures denote conceptual relationships such as part-whole, class inclusion, causeeffect, ete.</Paragraph>
    <Paragraph position="3"> 3. The shape primitives are on the level of primitive features rather than primitive shapes. By primitive features we mean, corners, convex, concave and planar surfaces and their like.</Paragraph>
    <Paragraph position="4"> 4. The labels of shapes, except in a few special cases, do not describe any shape properties and are derived from objects associated with that shape.</Paragraph>
    <Paragraph position="5"> 5. In order to preserve continuity, we need interpolation procedures. We assume that several such procedures exist, for example, clustering mechanisms, sampling p~ocedures, perspective transformations, rotation, etc. These are available as a general mechanisms for image processing.</Paragraph>
    <Paragraph position="6"> We certainly have not offered complete solutions to all the issues diseussed above, but we hope that we have raised several valid questions and suggested some approaches.</Paragraph>
  </Section>
class="xml-element"></Paper>