Using fully convolutional neural networks for object detection in robot welding applications

Simple item page
dc.contributor.advisorHeskes, T.M.
dc.contributor.advisorExner, E. Jr.
dc.contributor.authorDalen, J. van
dc.contributor.otherExner Ingenieurstechniek BVen_US
dc.date.issued2017-08-28
dc.description.abstractIn this thesis we have tried to use deep convolutional neural networks in a automated welding application. This application was the instant robot programming system from Exner. The network used was the fully convolutional U-net architecture because it performed well with few training examples, accepts inputs from most sizes and separates on a pixel level. The network was trained on a in this thesis created training set and able to separate most inputs correctly with an average recall rate of 86,80%.en_US
dc.embargo.lift3000-12-31
dc.identifier.urihttp://theses.ubn.ru.nl/handle/123456789/5255
dc.language.isoenen_US
dc.thesis.facultyFaculteit der Sociale Wetenschappenen_US
dc.thesis.specialisationMaster Artificial Intelligenceen_US
dc.thesis.studyprogrammeArtificial Intelligenceen_US
dc.thesis.typeMasteren_US
dc.titleUsing fully convolutional neural networks for object detection in robot welding applicationsen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Dalen van J._MSc_Thesis_2017_EMBARGO.pdf
Size:
10.31 MB
Format:
Adobe Portable Document Format
Description:
Thesis text
Download
Collections
Faculteit der Sociale Wetenschappen