Title :
Rotational invariant formulation for line process
Abstract :
The vector line field is used to restore rotational invariance. The energy function for the vector line field can be constructed in a rotationally invariant way by using vector calculus. This energy function can be used both in stochastic relaxation and in an analog neural net. An advantage of this method is the introduction of a constraint requiring that the edge direction be perpendicular to the direction of the steepest intensity change
Keywords :
neural nets; pattern recognition; relaxation theory; analog neural net; energy function; line process; rotational invariance; stochastic relaxation; vector line field;
Conference_Titel :
Neural Networks, 1990., 1990 IJCNN International Joint Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/IJCNN.1990.137806
