Presentation 1994/9/3
Image Restoration Using Layered Neural Networks and Hopfield Networks
Mitsuji Muneyasu, Kazunari Yamamoto, Takao Hinamoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) An algorithm is developed for the restoration of an image degraded by a known two-dimensional(2-D)shift-invariant point- spread function,and corrupted with white noise.A layered neural network and the Hopfield network are used for the edge detection, and the restoration and smoothing of a blurred image,respectively. In particular,A layered neural network is proposed for exact edge detection where the inputs consist of three pixel values and a local variance in a 2-D mask.This network can detect edges and suppress the noise in an image at the same time and its performance is adjusted by learning.Finally,some examples are given to illustrate the utility of the proposed algorithm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image restoration / Hopfield network / layered neural network / edge detection / reduction
Paper # CAS94-53
Date of Issue

Conference Information
Committee CAS
Conference Date 1994/9/3(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Circuits and Systems (CAS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image Restoration Using Layered Neural Networks and Hopfield Networks
Sub Title (in English)
Keyword(1) image restoration
Keyword(2) Hopfield network
Keyword(3) layered neural network
Keyword(4) edge detection
Keyword(5) reduction
1st Author's Name Mitsuji Muneyasu
1st Author's Affiliation Faculty of Engineering,Hiroshima University()
2nd Author's Name Kazunari Yamamoto
2nd Author's Affiliation Faculty of Engineering,Hiroshima University
3rd Author's Name Takao Hinamoto
3rd Author's Affiliation Faculty of Engineering,Hiroshima University
Date 1994/9/3
Paper # CAS94-53
Volume (vol) vol.94
Number (no) 214
Page pp.pp.-
#Pages 8
Date of Issue