Halftone/contone conversion using neural networks

Win Bin Huang, Wei Chen Chang, Yen Wei Lu, Wen-Yu Su, Yau-Hwang Kuo

Research output: Contribution to journalConference article

3 Citations (Scopus)

Abstract

A novel neural network based method for halftoning and inverse halftoning of digital images is presented. We first start from inverse half-toning of images produced from error diffusion methods using a RBF Network plus a MLP network. The restored contone images have had good quality already. Then, a SLP neural network is used to refine the halftoning processing and the training process of the inverse half-toning network is also involved. The combined training procedure produces half-tone images and the corresponding continuous tone images at the same time. It is found that these contone images have even better PSNR performance. Furthermore, the resulted half-tone images are visually sharper and clearer, too. The proposed inverse half-toning method is also compared to the well-known LUT method.

Original languageEnglish
Pages (from-to)3547-3550
Number of pages4
JournalProceedings - International Conference on Image Processing, ICIP
Volume2
Publication statusPublished - 2004 Dec 1
Event2004 International Conference on Image Processing, ICIP 2004 - , Singapore
Duration: 2004 Oct 182004 Oct 21

Fingerprint

Neural networks
Radial basis function networks
Processing

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

@article{12fc860263de49d1ac55bb92b5265e7a,
title = "Halftone/contone conversion using neural networks",
abstract = "A novel neural network based method for halftoning and inverse halftoning of digital images is presented. We first start from inverse half-toning of images produced from error diffusion methods using a RBF Network plus a MLP network. The restored contone images have had good quality already. Then, a SLP neural network is used to refine the halftoning processing and the training process of the inverse half-toning network is also involved. The combined training procedure produces half-tone images and the corresponding continuous tone images at the same time. It is found that these contone images have even better PSNR performance. Furthermore, the resulted half-tone images are visually sharper and clearer, too. The proposed inverse half-toning method is also compared to the well-known LUT method.",
author = "Huang, {Win Bin} and Chang, {Wei Chen} and Lu, {Yen Wei} and Wen-Yu Su and Yau-Hwang Kuo",
year = "2004",
month = "12",
day = "1",
language = "English",
volume = "2",
pages = "3547--3550",
journal = "Proceedings - International Conference on Image Processing, ICIP",
issn = "1522-4880",

}

Halftone/contone conversion using neural networks. / Huang, Win Bin; Chang, Wei Chen; Lu, Yen Wei; Su, Wen-Yu; Kuo, Yau-Hwang.

In: Proceedings - International Conference on Image Processing, ICIP, Vol. 2, 01.12.2004, p. 3547-3550.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Halftone/contone conversion using neural networks

AU - Huang, Win Bin

AU - Chang, Wei Chen

AU - Lu, Yen Wei

AU - Su, Wen-Yu

AU - Kuo, Yau-Hwang

PY - 2004/12/1

Y1 - 2004/12/1

N2 - A novel neural network based method for halftoning and inverse halftoning of digital images is presented. We first start from inverse half-toning of images produced from error diffusion methods using a RBF Network plus a MLP network. The restored contone images have had good quality already. Then, a SLP neural network is used to refine the halftoning processing and the training process of the inverse half-toning network is also involved. The combined training procedure produces half-tone images and the corresponding continuous tone images at the same time. It is found that these contone images have even better PSNR performance. Furthermore, the resulted half-tone images are visually sharper and clearer, too. The proposed inverse half-toning method is also compared to the well-known LUT method.

AB - A novel neural network based method for halftoning and inverse halftoning of digital images is presented. We first start from inverse half-toning of images produced from error diffusion methods using a RBF Network plus a MLP network. The restored contone images have had good quality already. Then, a SLP neural network is used to refine the halftoning processing and the training process of the inverse half-toning network is also involved. The combined training procedure produces half-tone images and the corresponding continuous tone images at the same time. It is found that these contone images have even better PSNR performance. Furthermore, the resulted half-tone images are visually sharper and clearer, too. The proposed inverse half-toning method is also compared to the well-known LUT method.

UR - http://www.scopus.com/inward/record.url?scp=20444499837&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20444499837&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:20444499837

VL - 2

SP - 3547

EP - 3550

JO - Proceedings - International Conference on Image Processing, ICIP

JF - Proceedings - International Conference on Image Processing, ICIP

SN - 1522-4880

ER -