The problem of parallelism detection between two curves has been formulated
in this paper as a line detection problem within an affine-invariant local
similarity matrix computed for the two curves. Each element of this matrix
gives an affine invariant measure of local parallelism for any pair of cur
ve segments along the two curves. This approach enables the detection of a
pair of parallel 3D planar curves as well as parallel 2D curves under gener
al affine transform. Two descriptors were also used here to provide a multi
-resolution representation of a curve. Since these two descriptors provide
sufficient local and semi-local shape information at every feature point on
the curves, the process of detecting parallelism is thus robust against bo
th noise and deformations. Moreover, the proposed technique allows all sign
ificant pairs of parallel segments within any two curves in the scene to be
detected. Experiments on detecting randomly affine-transformed curves, whi
ch are obtained from natural images or artificially generated images, have
demonstrated the effectiveness of the technique. (C) 2000 Pattern Recogniti
on Society. Published by Elsevier Science Ltd. All rights reserved.