By Topic

Binary representation and intensity surface interpolation of the grey level image by relaxation neural network models

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
N. Sonehara ; ATR Auditory & Visual Perception Res. Lab., Kyoto, Japan

Relaxation neural network models are studied to solve such basic image processing problems as binary quantization, effective sampling and interpolation. A relaxation neural network model is proposed to solve the spatial grey level representation problems in local and parallel computations. This network iteratively minimizes the energy function defined by the local error in neighboring picture elements. For effective binary representation depending on local features such as edges, interactions between binary processes and line processes representing discontinuities of the image are introduced. The applicability of the relaxation network model to intensity surface interpolation of the grey level image, from sparsely sampled data selected by fractal-based sampling, is discussed. A relaxation network model is used to interpolate the missing grey levels in parallel, which minimizes the energy function consisting of a membrane and thin plate, while preserving discontinuities of the image. The randomness controlled by the fractal dimension is introduced to the relaxation neural network model for the representation of small grey level changes

Published in:

Parallel and Distributed Processing, 1990. Proceedings of the Second IEEE Symposium on

Date of Conference:

9-13 Dec 1990