Improving robotic welding in the shipbuilding industry through the recognition of shipbuilding parts by pre-locating corners in images

David Sanders; Gareth Lambert; Lynn Pevy; Giles Tewkesbury

Improving robotic welding in the shipbuilding industry through the recognition of shipbuilding parts by pre-locating corners in images

David Sanders
, Gareth Lambert
, Lynn Pevy
, Giles Tewkesbury

Research output: Contribution to conference › Paper › peer-review

392 Downloads (Pure)

Abstract

A system is proposed that uses a combination of techniques to suggest weld requirements for ships parts. These suggestions are evaluated, decisions are made and then weld parameters are sent to a program generator. A pattern recognition system recognizes shipbuilding parts using shape contour information. Fourier-descriptors provide information and neural networks make decisions about shapes. The system has distinguished between various parts and programs have been generated so that the methods have proved to be valid approaches. The system has recently been improved by pre-processing using a simple and accurate corner-finder to find corners in an edge detected image.

Original language	English
Publication status	Published - May 2009
Event	8th International Conference on Computer Applications and Information Technology in the Maritime Industries - Budapest Duration: 10 May 2009 → 12 May 2009

Conference

Conference	8th International Conference on Computer Applications and Information Technology in the Maritime Industries
City	Budapest
Period	10/05/09 → 12/05/09

Access to Document

Gareth_ICCAS_Conf_Paper_Improving_robotic_welding_FormattedAccepted author manuscript (Post-print), 322 KB

Welding
Sanders, D. (PI), Rasol, Z. (CoI), Lambert, G. (CoI) & Tewkesbury, G. (CoI)
6/05/02 → 5/04/07
Project: Research

Cite this

@conference{c7776c44e4274389bd6ae6d9f44fd5fe,

title = "Improving robotic welding in the shipbuilding industry through the recognition of shipbuilding parts by pre-locating corners in images",

abstract = "A system is proposed that uses a combination of techniques to suggest weld requirements for ships parts. These suggestions are evaluated, decisions are made and then weld parameters are sent to a program generator. A pattern recognition system recognizes shipbuilding parts using shape contour information. Fourier-descriptors provide information and neural networks make decisions about shapes. The system has distinguished between various parts and programs have been generated so that the methods have proved to be valid approaches. The system has recently been improved by pre-processing using a simple and accurate corner-finder to find corners in an edge detected image.",

author = "David Sanders and Gareth Lambert and Lynn Pevy and Giles Tewkesbury",

year = "2009",

month = may,

language = "English",

note = "8th International Conference on Computer Applications and Information Technology in the Maritime Industries ; Conference date: 10-05-2009 Through 12-05-2009",

}

Improving robotic welding in the shipbuilding industry through the recognition of shipbuilding parts by pre-locating corners in images. / Sanders, David; Lambert, Gareth; Pevy, Lynn et al.
2009. Paper presented at 8th International Conference on Computer Applications and Information Technology in the Maritime Industries, Budapest.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Improving robotic welding in the shipbuilding industry through the recognition of shipbuilding parts by pre-locating corners in images

AU - Sanders, David

AU - Lambert, Gareth

AU - Pevy, Lynn

AU - Tewkesbury, Giles

PY - 2009/5

Y1 - 2009/5

N2 - A system is proposed that uses a combination of techniques to suggest weld requirements for ships parts. These suggestions are evaluated, decisions are made and then weld parameters are sent to a program generator. A pattern recognition system recognizes shipbuilding parts using shape contour information. Fourier-descriptors provide information and neural networks make decisions about shapes. The system has distinguished between various parts and programs have been generated so that the methods have proved to be valid approaches. The system has recently been improved by pre-processing using a simple and accurate corner-finder to find corners in an edge detected image.

AB - A system is proposed that uses a combination of techniques to suggest weld requirements for ships parts. These suggestions are evaluated, decisions are made and then weld parameters are sent to a program generator. A pattern recognition system recognizes shipbuilding parts using shape contour information. Fourier-descriptors provide information and neural networks make decisions about shapes. The system has distinguished between various parts and programs have been generated so that the methods have proved to be valid approaches. The system has recently been improved by pre-processing using a simple and accurate corner-finder to find corners in an edge detected image.

M3 - Paper

T2 - 8th International Conference on Computer Applications and Information Technology in the Maritime Industries

Y2 - 10 May 2009 through 12 May 2009

ER -

Improving robotic welding in the shipbuilding industry through the recognition of shipbuilding parts by pre-locating corners in images

Abstract

Conference

Access to Document

Fingerprint

Projects

Welding

Cite this