Regularized image reconstruction using SVD and a neural network method for matrix inversion
RJ Steriti, MA Fiddy - IEEE Transactions on Signal Processing, 1993 - ieeexplore.ieee.org
RJ Steriti, MA Fiddy
IEEE Transactions on Signal Processing, 1993•ieeexplore.ieee.orgTwo methods of matrix inversion are compared for use in an image reconstruction algorithm.
The first is based on energy minimization using a Hopfield neural network. This is compared
with the inverse obtained using singular value decomposition (SVD). It is shown for a
practical example that the neural network provides a more useful and robust matrix
inverse.<>
The first is based on energy minimization using a Hopfield neural network. This is compared
with the inverse obtained using singular value decomposition (SVD). It is shown for a
practical example that the neural network provides a more useful and robust matrix
inverse.<>
Two methods of matrix inversion are compared for use in an image reconstruction algorithm. The first is based on energy minimization using a Hopfield neural network. This is compared with the inverse obtained using singular value decomposition (SVD). It is shown for a practical example that the neural network provides a more useful and robust matrix inverse.<>
ieeexplore.ieee.org