DocumentCode
1056174
Title
Regularized image reconstruction using SVD and a neural network method for matrix inversion
Author
Steriti, Ronald J. ; Fiddy, Michael A.
Author_Institution
Dept. of Electr. Eng., Massachusetts Univ., Lowell, MA, USA
Volume
41
Issue
10
fYear
1993
fDate
10/1/1993 12:00:00 AM
Firstpage
3074
Lastpage
3077
Abstract
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
Keywords
Hopfield neural nets; image reconstruction; inverse problems; matrix algebra; Hopfield neural network; SVD; energy minimization; image reconstruction; matrix inversion; regularisation technique; robust matrix inverse; singular value decomposition; Discrete Fourier transforms; Frequency estimation; Hopfield neural networks; Image reconstruction; Matrices; Matrix decomposition; Neural networks; Productivity; Robustness; Singular value decomposition;
fLanguage
English
Journal_Title
Signal Processing, IEEE Transactions on
Publisher
ieee
ISSN
1053-587X
Type
jour
DOI
10.1109/78.277813
Filename
277813
Link To Document