Real Time Defect Detection for Timber Industry with Deep Neural Networks

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.advisorEskola, Kalle
dc.contributor.authorGuo, Gelin
dc.contributor.schoolPerustieteiden korkeakoulufi
dc.contributor.supervisorIlin, Alexander
dc.date.accessioned2020-08-23T17:10:44Z
dc.date.available2020-08-23T17:10:44Z
dc.date.issued2020-08-18
dc.description.abstractAutomatic timber grading requires fast, accurate and consistent defect detection to support downstream solution optimization. Traditional image processing techniques based on handcrafted feature descriptors are sensitive to scanning disturbance and often require extensive domain knowledge to develop. In this master’s thesis, we develop a method to perform accurate wood defect detection in real time based on deep neural network models. We address the problem of imbalanced defect distribution in the dataset by combining type aggregation and effective sampling, such that infrequent defects can be detected well despite inadequate annotations. On the production dataset provided by FinScan Oy, our model achieved a mean average precision of 11.63% for all 12 different wood defects and an average precision of 42.27% for dead knots, which are the most influential defects in final grading. On the RTX 2080Ti GPU, the model runs at 25 frames per second which brings a potential throughput of 250 boards per minute for the saw line.en
dc.format.extent50+1
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/46060
dc.identifier.urnURN:NBN:fi:aalto-202008234992
dc.language.isoenen
dc.programmeMaster’s Programme in Computer, Communication and Information Sciencesfi
dc.programme.majorMachine Learning, Data Science and Artificial Intelligencefi
dc.programme.mcodeSCI3044fi
dc.subject.keyworddeep learningen
dc.subject.keywordautomatic timber gradingen
dc.subject.keywordconvolutional neural networksen
dc.subject.keywordwood defect detectionen
dc.subject.keywordeffective samplingen
dc.subject.keywordcomputer visionen
dc.titleReal Time Defect Detection for Timber Industry with Deep Neural Networksen
dc.typeG2 Pro gradu, diplomityöfi
dc.type.ontasotMaster's thesisen
dc.type.ontasotDiplomityöfi
local.aalto.electroniconlyyes
local.aalto.openaccessno

Files