Title :
Weight adjustment rule of neural networks for computing discrete 2-D Gabor transforms [image processing]
Author :
Yan, Hong ; Gore, John C.
Author_Institution :
Sch. of Electr. Eng., Sydney Univ., NSW, Australia
fDate :
9/1/1990 12:00:00 AM
Abstract :
It is demonstrated that the weight adjustment rule used in the neural network for computing the 2-D Gabor transform proposed by J. Daugman (1988) can be shown to be equivalent to the Jacobi iteration scheme for solving simultaneous linear equations. It is shown that faster convergence, of the algorithm can be achieved by using Gauss-Seidel iteration, successive overrelaxation, conjugate gradient algorithms, and multigrid methods
Keywords :
conjugate gradient methods; convergence of numerical methods; iterative methods; neural nets; picture processing; transforms; Gauss-Seidel iteration; Jacobi iteration scheme; conjugate gradient algorithms; convergence; discrete 2-D Gabor transforms; image processing; multigrid methods; neural networks; simultaneous linear equations; successive overrelaxation; weight adjustment rule; Computer networks; Discrete transforms; Equations; Error correction; Image analysis; Image coding; Jacobian matrices; Least squares methods; Neural networks; Signal processing algorithms;
Journal_Title :
Acoustics, Speech and Signal Processing, IEEE Transactions on
