International journal of computer vision vol:14 issue:1 pages:49-65
Methods for the recognition of planar shapes from arbitrary viewpoints are described. The adopted model of projection is orthographic. The invariant descriptions derived for this group are one-dimensional shape signatures comparable to the well-known curvature as a function of arc length description of Euclidean geometry. Since the use of such differential invariants in the affine case would lead to unacceptably high orders of derivatives, affine invariant descriptions based on semi-differential invariants are proposed as an alternative. A systematic discussion of different types of these invariants is given. The usefulness and viability of this methodology is demonstrated on a database containing more than 40 objects.