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
Comparing performance of convolutional neural network models on a novel car classification task
KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
2017 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Jämförelse av djupa neurala nätverksmodeller med faltning på en ny bilklassificeringsuppgift (Swedish)
Abstract [en]

Recent neural network advances have lead to models that can be used for a variety of image classification tasks, useful for many of today’s media technology applications. In this paper, I train hallmark neural network architectures on a newly collected vehicle image dataset to do both coarse- and fine-grained classification of vehicle type. The results show that the neural networks can learn to distinguish both between many very different and between a few very similar classes, reaching accuracies of 50.8% accuracy on 28 classes and 61.5% in the most challenging 5, despite noisy images and labeling of the dataset.

Abstract [sv]

Nya neurala nätverksframsteg har lett till modeller som kan användas för en mängd olika bildklasseringsuppgifter, och är därför användbara många av dagens medietekniska applikationer. I detta projektet tränar jag moderna neurala nätverksarkitekturer på en nyuppsamlad bilbild-datasats för att göra både grov- och finkornad klassificering av fordonstyp. Resultaten visar att neurala nätverk kan lära sig att skilja mellan många mycket olika bilklasser,  och även mellan några mycket liknande klasser. Mina bästa modeller nådde 50,8% träffsäkerhet vid 28 klasser och 61,5% på de mest utmanande 5, trots brusiga bilder och manuell klassificering av datasetet.

Place, publisher, year, edition, pages
2017. , p. 14
Keywords [en]
neural network, convolution, car, vehicle, classification, recognition, supervised learning, machine learning, computer science
National Category
Media and Communication Technology
Identifiers
URN: urn:nbn:se:kth:diva-213468OAI: oai:DiVA.org:kth-213468DiVA, id: diva2:1137670
Subject / course
Media Technology
Educational program
Bachelor of Science in Engineering - Computer Engineering
Presentation
2017-08-25, Samtalsrum 1439, LINDSTEDTSVÄGEN 3, Stockholm, 19:01 (English)
Examiners
Available from: 2017-10-19 Created: 2017-08-31 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

fulltext(3010 kB)266 downloads
File information
File name FULLTEXT01.pdfFile size 3010 kBChecksum SHA-512
1287d9944aff2cff1149d9bf5e8100d3e681a6c40d6c026cea7da37404cf385b1ad429df0dca18cc3e77c51878747871a40866b5fcda96faec8bcd50c47fdcde
Type fulltextMimetype application/pdf

By organisation
Media Technology and Interaction Design, MID
Media and Communication Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 266 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: 271 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