DocumentCode
314311
Title
Multiscale image factorization
Author
Johnson, John L. ; Padgett, Mary Lou ; Friday, William A.
Author_Institution
Res. Dev. & Eng. Center, US Army Missile Command, Redstone Arsenal, AL, USA
Volume
3
fYear
1997
fDate
9-12 Jun 1997
Firstpage
1465
Abstract
A new hierarchical image decomposition is described which resolves an image into a set of image product factors. The set is ordered in scale from coarse to fine image detail. When the factored set is multiplied together it reproduces the original image. By selecting factors, coarse scene elements such as shadows and fine scene factors such as noise, can be isolated. The scale of detail is controlled by the linking strength of a pulse coupled neural network, on which the system is based
Keywords
image segmentation; neural nets; synchronisation; coarse image; fine image; hierarchical image decomposition; image product factors; multiscale image factorization; pulse coupled neural network; Biological system modeling; Fires; Image processing; Joining processes; Layout; Neural networks; Optical arrays; Pulse generation; Pulse modulation; Signal processing;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks,1997., International Conference on
Conference_Location
Houston, TX
Print_ISBN
0-7803-4122-8
Type
conf
DOI
10.1109/ICNN.1997.614011
Filename
614011
Link To Document