Issac Weiss,
Noise-resistant invariants of curves,
IEEE Transactions on Pattern Analysis and Machine Intelligence,
15, 9, pp. 943-948, September 1993.
Issac Weiss,
Noise-resistant invariants of curves,
IEEE Transactions on Pattern Analysis and Machine Intelligence,
15, 9, pp. 943-948, September 1993.Projective invariants are shape descriptors that are independent of the point of view from which the shape is seen, and therefore, they are of major importance in object recognition. They make it possible to match an image of an object to one stored in a database without the need to search for the correct viewpoint. In this paper, we obtain an invariant representation (``signature'') of a general curve. the calculation is local and does not suffer from the occlusion problem of global descriptors. To make the method robust, we have developed differentiation techniques that give much more reliable results than previous ones. These differentiation methods are useful in many other applications as well.