Accession Number : ADA259515


Title :   Developing a Neural Network to Act as a Noise Filter


Descriptive Note : Final rept. Sep 1991-Sep 1992


Corporate Author : ARMY ARMAMENT MUNITIONS AND CHEMICAL COMMAND ROCK ISLAND IL


Personal Author(s) : Rivero, Ramon


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a259515.pdf


Report Date : 02 Oct 1992


Pagination or Media Count : 142


Abstract : This study uses the neural network simulator called NETS to determine if neural networks could perform a non-linear filtering operation to remove noise from two-dimensional (2-D) data and produce a noise-free image. Application is geared toward the development and performance of neural network filters, including the development of an optional neural network architecture and the use of-criteria in determining how accurate the net filtered noise-to produce a noise-free image.


Descriptors :   *NEURAL NETS , *LINEAR FILTERING , *NOISE , SIMULATORS , OPERATION , FILTRATION , ARCHITECTURE , FILTERS , IMAGES , NETWORKS


Subject Categories : Computer Programming and Software
      Acoustics


Distribution Statement : APPROVED FOR PUBLIC RELEASE