A unified neutral network approach to digital image halftoning
IEEE Transactions on Signal ProcessingPublished 1 April 1991Open access
Stefanos Kollias, Dimitris Anastassiou
Citations32
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A technique for digital halftoning of images that is based on a symmetric parallel formulation of the error diffusion halftoned method is developed, based on the minimization of a frequency-weighted mean-squared error criterion.
Abstract
A technique for digital halftoning of images that is based on a symmetric parallel formulation of the error diffusion halftoning method is developed. Appropriately trained or designed near-neighbor-connected symmetric neural networks are used to generate halftoned images in an efficient parallel way, based on the minimization of a frequency-weighted mean-squared error criterion. Image halftoning by symmetric networks is described using an appropriate image distortion measure. The problem of determining the network interconnection weights is examined. Examples which illustrate the performance of the proposed technique compared to that of conventional or more complex methods are given.
Keywords
Computer ScienceEngineeringPhysics and Astronomy
The MIT Press eBooksParallel Distributed Processing
15,227 Citations1986David E. Rumelhart, James L. McClelland +1 more
Biological Cybernetics“Neural” computation of decisions in optimization problems
6,040 Citations1985J. J. Hopfield, David W. Tank
Results of computer simulations of a network designed to solve a difficult but well-defined optimization problem-the Traveling-Salesman Problem-are presented and used to illustrate the computational power of the networks.
IEEE Transactions on Circuits and SystemsSimple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit
2,173 Citations1986David W. Tank, J. J. Hopfield
It is described how several optimization problems can be rapidly solved by highly interconnected networks of simple analog processors, and it is shown that a network which solves linear programming Problems can be understood from the same concepts.
IEEE Transactions on Information TheoryThe effects of a visual fidelity criterion of the encoding of images
1,054 Citations1974James L. Mannos, D. Sakrison
This investigation has considered a class of distortion measures for which it is possible to simulate the optimum (in a rate-distortion sense) encoding and found one distortion measure was fairly consistently rated as yielding the most satisfactory appearing encoded images.
Computer Graphics and Image ProcessingA survey of techniques for the display of continuous tone pictures on bilevel displays
566 Citations1976J. F. Jarvis, Charles N. Judice +1 more
This work presents a survey of processing techniques for presenting continuous tone still images on such displays by dividing an image into picture elements and comparing the intensity of each element with a threshold value.
IEEE Transactions on Acoustics Speech and Signal ProcessingImage restoration using a neural network
411 Citations1988Yanjun Zhou, Rama Chellappa +2 more
An approach for restoration of gray level images degraded by a known shift invariant blur function and additive noise is presented using a neural computational network and a high-quality image is obtained using this approach.
Proceedings of the IEEEDithering with blue noise
407 Citations1988Robert Ulichney
The concept of blue noise-high-frequency white noise-is introduced and found to have desirable properties for halftoning, and efficient algorithms for dithering with blue noise, based on perturbed error diffusion, are developed.
IEEE Transactions on Circuits and SystemsAn adaptive least squares algorithm for the efficient training of artificial neural networks
198 Citations1989Stefanos Kollias, Dimitris Anastassiou
A novel learning algorithm is developed for the training of multilayer feedforward neural networks, based on a modification of the Marquardt-Levenberg least-squares optimization method, which has better convergence properties than the conventional backpropagation learning technique.
IBM Journal of Research and DevelopmentImage processing by simulated annealing
141 Citations1985P. Carnevali, Luke J. Coletti +1 more
It is shown that simulated annealing, a statistical mechanics method recently proposed as a tool in solving complex optimization problems, can be used in problems arising in image processing, and some of these problems are formally equivalent to ground state problems for two-dimensional Ising spin systems.
IEEE Transactions on Circuits and SystemsError diffusion coding for A/D conversion
120 Citations1989Dimitris Anastassiou
It is shown that concepts and structures used in digital image halftoning are directly applicable to oversampled sigma-delta modulation of sound signals and a novel kind of parallel analog network is introduced and shown to be appropriate for this task.
Electronics LettersSwitched-capacitor neural networks
102 Citations1987Y. Tsividis, Dimitris Anastassiou
IEEE Transactions on Acoustics Speech and Signal ProcessingA fast multichannel approach to adaptive image estimation
36 Citations1989Yiannis S. Boutalis, Stefanos Kollias +1 more
It is shown that the method, named the fast multichannel space recursive estimation technique (FAMSRET), can overcome image boundary discontinuity problems by processing consecutive image lines in opposite directions.
Design of a half-toning integrated circuit based on analog quadratic minimization by non linear multistage switched capacitor network
18 Citations2003Thierry Bernard, Patrick Garda +3 more
The authors present the design of a neural network performing the minimization of a quadratic distance between the analog acquired picture and a convolution of the resulting halftoned binary picture, showing that using a diffusion kernel and switched-capacitor networks results in an effective halftoning circuit.