Kevin W. Bowyer - Aspect Graphs

  • Aspect Graphs and Their Use in Object Recognition,
    David Eggert, Louise Stark, and Kevin W. Bowyer,
    Annals of Mathematics and Artificial Intelligence 13, 347-375, 1995.

  • The Scale Space Aspect Graph,
    David W. Eggert, Kevin W. Bowyer, Charles R. Dyer, Henrik I. Christensen, and Dmitry B. Goldgof.
    IEEE Transactions on Pattern Analysis and Machine Intelligence 15 (11), 1114-1130, November 1993.
    pdf of this paper.
    This paper introduces the concept of the scale space aspect graph, defines three different interpretations of the scale dimension, and presents a detailed example for a simple class of objects, with scale defined in terms of the spatial extent of features in the image.

  • Computing the Generalized Aspect Graph for Objects with Moving Parts,
    Kevin W. Bowyer, Maha Y. Sallam, David Eggert, and John H. Stewman,
    IEEE Transactions on Pattern Analysis and Machine Intelligence 15 (6), 605-610, June 1993.
    A number of researchers have described algorithms for computing the aspect graph representation, but this work has thus far been limited to entirely rigid objects. We generalize this concept to include a larger, more realistic domain of objects known as articulated assemblies, those objects composed of rigid parts with articulated connections allowed between parts.

  • Computing the Perspective Projection Aspect Graph of Solids of Revolution,
    David W. Eggert and Kevin W. Bowyer,
    IEEE Transactions on Pattern Analysis and Machine Intelligence 15 (2), 109-128, February 1993.
    This paper presents the first (only) implemented algorithm to compute the aspect graph for a class of curved-surface objects based on an exact parcellation of 3-D viewpoint space. The class of objects considered is solids of revolution. ... the worst-case complexity of ... the number of cells in the aspect graph is is O(N^4), where N is the degree of a polynomial that defines the object shape.

  • Achieving Generalized Object Recognition Through Reasoning About Association of Function To Structure,
    Louise Stark and Kevin W. Bowyer,
    IEEE Transactions on Pattern Analysis and Machine Intelligence 13 (10), 1097-1104, October 1991.
    pdf of this paper.
    The purpose of the work described here is to demonstrate the feasibility of defining an object category in terms of the functional properties shared by all objects in the category. ... A complete system has been implemented that takes the boundary surface description of a 3-D object as its input and attempts to recognize whether the object belongs to the category chair ... This is, to our knowledge the first (only) implemented system to explore the use of a purely function-based definition of an object category ... to recognize 3-D objects.

  • Aspect Graphs: An Introduction and Survey of Recent Results,
    Kevin W. Bowyer and Charles R. Dyer,
    International Journal of Imaging Systems and Technologies 2, 315-328, 1990.

  • Direct Construction of Perspective Projection Aspect Graphs for Planar-Face Convex Objects,
    John Stewman and Kevin W. Bowyer,
    Computer Vision, Graphics and Image Processing 51 (1), 20-37, July 1990.