Abstract

We explore a method of representing solid shape that is useful for visual recognition. We assume that complex shapes are constructed from convex, compact shapes and that construction involves three operations: solid union (to form humps), solid subtraction (to leave dents), and smoothing (to remove discontinuities). The boundaries between shapes joined through these operations are contours of extrema of a principal curvature. Complex objects can be decomposed along these boundaries into convex shapes, the so-called parts. We suggest that this decomposition into parts forms the basis for a shape memory. We show that the part boundaries of an object can be inferred from its occluding contours, at least up to a number of ambiguities.

© 1987 Optical Society of America

Inferring three-dimensional shapes from two-dimensional silhouettes

W. A. Richards, Jan J. Koenderink, and D. D. Hoffman
J. Opt. Soc. Am. A 4(7) 1168-1175 (1987)

Encoding contour shape by curvature extrema

Whitman Richards, Benjamin Dawson, and Douglas Whittington
J. Opt. Soc. Am. A 3(9) 1483-1491 (1986)

Perception of surface contours and surface shape: from computation to psychophysics

David C. Knill
J. Opt. Soc. Am. A 9(9) 1449-1464 (1992)

Estimation of contour motion and deformation for nonrigid object tracking

Jie Shao, Fatih Porikli, and Rama Chellappa
J. Opt. Soc. Am. A 24(8) 2109-2121 (2007)

Incremental rigidity scheme for recovering structure from motion: position-based versus velocity-based formulations

Norberto M. Grzywacz and Ellen C. Hildreth
J. Opt. Soc. Am. A 4(3) 503-518 (1987)