A model is described for image segmentation that tries to capture the low-level depth reconstruction exhibited in early human vision, giving an important role to edge terminations. The problem is to find a decomposition of the domain D of an image that has a minimum of disrupted edges-junctions of edges, crack tips, corners, and cusps-by creating suitable continuations for the disrupted edges behind occluding regions. The result is a decomposition of D into overlapping regions R/sub 1/ union . . . union R/sub n/ ordered by occlusion, which is called the 2.1-D sketch. Expressed as a minimization problem, the model gives rise to a family of optimal contours, called nonlinear splines, that minimize length and the square of curvature. These are essential in the construction of the 2.1-D sketch of an image, as the continuations of disrupted edges. An algorithm is described that constructs the 2.1-D sketch of an image, and gives results for several example images. The algorithm yields the same interpretations of optical illusions as the human visual system.<<ETX>>
[1]
A. Love.
A treatise on the mathematical theory of elasticity
,
1892
.
[2]
Azriel Rosenfeld,et al.
Gray-level corner detection
,
1982,
Pattern Recognit. Lett..
[3]
R. von der Heydt,et al.
Illusory contours and cortical neuron responses.
,
1984,
Science.
[4]
P. Griffiths,et al.
Reduction for Constrained Variational Problems and κ 2 2 ds
,
1986
.
[5]
D. Mumford,et al.
Optimal approximations by piecewise smooth functions and associated variational problems
,
1989
.
[6]
K Nakayama,et al.
Toward a neural understanding of visual surface representation.
,
1990,
Cold Spring Harbor symposia on quantitative biology.