Image inpainting methods by using CELLULAR neural networks

Alexandra Gacsádi, P. Szolgay

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Some CNN methods are presented that can be used for the reconstruction of damaged or partially known images. The proposed methods take the possibility of direct implementation on an existing CNN chip into account, in a single step, by using 3*3 dimensional linear reaction templates. Due to complete parallel processing, computational time reduction is achieved. Efficiency of these methods can be increased by combining them with nonlinear template that ensures the growth of the local properties spreading area along with regional ones.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications
EditorsT. Roska, B.E. Shi, Z. Chen, C.-T. Lin, C. Rekeczky
Pages198-201
Number of pages4
Publication statusPublished - 2005
Event9th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA - Hsinchu, Taiwan, Province of China
Duration: May 28 2005May 30 2005

Other

Other9th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA
CountryTaiwan, Province of China
CityHsinchu
Period5/28/055/30/05

Fingerprint

Neural networks
Processing

ASJC Scopus subject areas

  • Software

Cite this

Gacsádi, A., & Szolgay, P. (2005). Image inpainting methods by using CELLULAR neural networks. In T. Roska, B. E. Shi, Z. Chen, C-T. Lin, & C. Rekeczky (Eds.), Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications (pp. 198-201)

Image inpainting methods by using CELLULAR neural networks. / Gacsádi, Alexandra; Szolgay, P.

Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. ed. / T. Roska; B.E. Shi; Z. Chen; C.-T. Lin; C. Rekeczky. 2005. p. 198-201.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gacsádi, A & Szolgay, P 2005, Image inpainting methods by using CELLULAR neural networks. in T Roska, BE Shi, Z Chen, C-T Lin & C Rekeczky (eds), Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. pp. 198-201, 9th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA, Hsinchu, Taiwan, Province of China, 5/28/05.
Gacsádi A, Szolgay P. Image inpainting methods by using CELLULAR neural networks. In Roska T, Shi BE, Chen Z, Lin C-T, Rekeczky C, editors, Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. 2005. p. 198-201
Gacsádi, Alexandra ; Szolgay, P. / Image inpainting methods by using CELLULAR neural networks. Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. editor / T. Roska ; B.E. Shi ; Z. Chen ; C.-T. Lin ; C. Rekeczky. 2005. pp. 198-201
@inproceedings{cb51de22aa0a479a9bc331d52252be1c,
title = "Image inpainting methods by using CELLULAR neural networks",
abstract = "Some CNN methods are presented that can be used for the reconstruction of damaged or partially known images. The proposed methods take the possibility of direct implementation on an existing CNN chip into account, in a single step, by using 3*3 dimensional linear reaction templates. Due to complete parallel processing, computational time reduction is achieved. Efficiency of these methods can be increased by combining them with nonlinear template that ensures the growth of the local properties spreading area along with regional ones.",
author = "Alexandra Gacs{\'a}di and P. Szolgay",
year = "2005",
language = "English",
pages = "198--201",
editor = "T. Roska and B.E. Shi and Z. Chen and C.-T. Lin and C. Rekeczky",
booktitle = "Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications",

}

TY - GEN

T1 - Image inpainting methods by using CELLULAR neural networks

AU - Gacsádi, Alexandra

AU - Szolgay, P.

PY - 2005

Y1 - 2005

N2 - Some CNN methods are presented that can be used for the reconstruction of damaged or partially known images. The proposed methods take the possibility of direct implementation on an existing CNN chip into account, in a single step, by using 3*3 dimensional linear reaction templates. Due to complete parallel processing, computational time reduction is achieved. Efficiency of these methods can be increased by combining them with nonlinear template that ensures the growth of the local properties spreading area along with regional ones.

AB - Some CNN methods are presented that can be used for the reconstruction of damaged or partially known images. The proposed methods take the possibility of direct implementation on an existing CNN chip into account, in a single step, by using 3*3 dimensional linear reaction templates. Due to complete parallel processing, computational time reduction is achieved. Efficiency of these methods can be increased by combining them with nonlinear template that ensures the growth of the local properties spreading area along with regional ones.

UR - http://www.scopus.com/inward/record.url?scp=27144498914&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27144498914&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:27144498914

SP - 198

EP - 201

BT - Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications

A2 - Roska, T.

A2 - Shi, B.E.

A2 - Chen, Z.

A2 - Lin, C.-T.

A2 - Rekeczky, C.

ER -