Shape Representation and Recognition from Multiscale Curvature

Gregory Dudek, John K. Tsotsos

Computer Vision and Image Understanding

Volume 68, Number 2, Pages 170-189, 1997




Motivation

Effective methods for representing shapes are useful for shape recognition and comparison in computer vision.

Goal of This Research

The authors wish to derive a shape representation technique that is useful for shape recognition and comparison. In particular they focus on concisely describing shapes based on curvature properties at various scales.

Goal of This Paper

This paper presents a shape decomposition operation which simultaneously performs data interpolation, data smoothing, and segmentation. Each minimization operator has curvature tuning and a different spatial sensitivity function, so the different possible descriptions capture curvature information at multiple scales. These minimization operators are collectively called curvature-tuned smoothing (CTS). The shape description method is multiscale, but the notion of scale is based on curvature-scale space rather than the conventional definition in terms of Gaussian blurring and spatial frequency.

Two parameters must be specified when applying this technique:

  1. Sampling grid for curvature space
  2. Scalar value that determines relevance of the model set

Related Work

Results

The shape description technique presented in this paper has many advantages in recognition of curved objects, including:
  1. Objects which are similar but have no identical subcontours can still be matched, unlike many existing methods
  2. Noise is generally captured in the lower levels of the multiscale representation as desired, so higher levels of similar shapes with different types of noise still tend to match well
  3. The method handles open curves, closed curves, and primitives from the visible part of an occluded curve
  4. Many natural objects can be described in one way; the CTS method allows multiple ``good" representations of any single region
  5. Curvature information is not corrupted by smoothing
  6. The description is computed using local computations, so fast parallel implementations seem possible
  7. The CTS representation is applicable to recognition and matching
The method's main shortcoming is that it models objects as being locally approximately circular or quadric in shape. For a wide range of smoothly curved objects, this assumption seems appropriate. However for rough objects this may be inappropriate.

Further issues to be explored include:

  1. Complete development of CTS-based surface recognition
  2. Inference of volumetric models from the curvature-based segments
  3. Reconstruction of original data from CTS description

Bibliography



ctj