kth.sePublications KTH
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Graphical Glitch Detection in Video Games Using CNNs
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematical Statistics.
2020 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Användning av CNNs för att upptäcka felaktiga bilder i videospel (Swedish)
Abstract [en]

This work addresses the following research question: Can we detect videogame glitches using Convolutional Neural Networks? Focusing on the most common types of glitches, texture glitches (Stretched, Lower Resolution, Missing, and Placeholder). We first systematically generate a dataset with both images with texture glitches and normal samples. 

To detect the faulty images we try both Classification and Semantic Segmentation approaches, with a clear focus on the former. The best setting in classification uses a ShuffleNetV2 architecture and obtains precisions of 80.0%, 64.3%, 99.2%, and 97.0% in the respective glitch classes Stretched, Lower Resolution, Missing, and Placeholder. All of this with a low false positive rate of 6.7%.

To complement this study, we also discuss how the models extrapolate to different graphical environments, which are the main sources of confusion for the model, how to estimate the confidence of the network, and ways to interpret the internal behavior of the models.

Abstract [sv]

Detta projekt svarar på följande forskningsfråga: Kan man använda Convolutional Neural Networks för att upptäcka felaktiga bilder i videospel? Vi fokuserar på de vanligast förekommande grafiska defekter i videospel, felaktiga textures (sträckt, lågupplöst, saknas och platshållare). Med hjälp av en systematisk process genererar vi data med både normala och felaktiga bilder.

För att hitta defekter använder vi CNN via både Classification och Semantic Segmentation, med fokus på den första metoden. Den bäst presterande Classification-modellen baseras på ShuffleNetV2 och når 80.0%, 64.3%, 99.2% och 97.0% precision på respektive sträckt-, lågupplöst-, saknas- och platshållare-buggar. Detta medan endast 6.7% av negativa datapunkter felaktigt klassifieras som positiva.

Denna undersökning ser även till hur modellen generaliserar till olika grafiska miljöer, vilka de primära orsakerna till förvirring hos modellen är, hur man kan bedöma säkerheten i nätverkets prediktion och hur man bättre kan förstå modellens interna struktur.

Place, publisher, year, edition, pages
2020.
Series
TRITA-SCI-GRU ; 2020:090
Keywords [en]
Convolutional Neural Networks, Glitch Detection, Computer Vision, Supervised Anomaly Detection, Deep Learning
Keywords [sv]
Konvolutionnella nervnätverk, Glitch Detection, Datorsyn, Övervakad avvikelse av anomali, Djup lärning
National Category
Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:kth:diva-273574OAI: oai:DiVA.org:kth-273574DiVA, id: diva2:1432668
External cooperation
EA SEED
Subject / course
Mathematical Statistics
Educational program
Master of Science - Applied and Computational Mathematics
Supervisors
Examiners
Available from: 2020-05-29 Created: 2020-05-27 Last updated: 2022-06-26Bibliographically approved

Open Access in DiVA

fulltext(42296 kB)2088 downloads
File information
File name FULLTEXT01.pdfFile size 42296 kBChecksum SHA-512
5adb75443ed31dbb0f172e62400fa39acfe79b4a1d72b511efa10a4194b91714450e2349886b65661d0447516c52c6aa816a7aefa1343bee450dbc11ec6a8530
Type fulltextMimetype application/pdf

By organisation
Mathematical Statistics
Probability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar
Total: 2088 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 1296 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf