The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.09 - September (1993 vol.15)
pp: 943-948
ABSTRACT
<p>Projective invariants are shape descriptors that are independent of the point of view from which the shape is seen, and, therefore, 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 for searching for the correct viewpoint. An invariant representation of a general curve is obtained. The calculation is local and does not suffer from the occlusion problem of global descriptors. To make the method robust, differentiation techniques that give much more reliable results than previous ones are developed. These differentiation methods are useful in many other applications as well.</p>
INDEX TERMS
noise-resistant projective invariants; robustness; curve invariants; shape descriptors; object recognition; occlusion; differentiation techniques; image recognition
CITATION
I. Weiss, "Noise-Resistant Invariants of Curves", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.15, no. 9, pp. 943-948, September 1993, doi:10.1109/34.232081
19 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool