Repository logo
 

ANALYZING STYLE TRANSFER ALGORITHMS FOR SEGMENTED IMAGES

dc.contributor.advisorDr. David Hart
dc.contributor.authorSeyed, Seyedhadi
dc.contributor.committeeMemberDr. Rui Wu
dc.contributor.committeeMemberDr. Nic Herndon
dc.contributor.departmentComputer Science
dc.date.accessioned2025-01-28T17:00:54Z
dc.date.available2025-01-28T17:00:54Z
dc.date.created2024-12
dc.date.issuedDecember 2024
dc.date.submittedDecember 2024
dc.date.updated2025-01-26T14:14:49Z
dc.degree.collegeCollege of Engineering and Technology
dc.degree.grantorEast Carolina University
dc.degree.majorMS-Data Science
dc.degree.nameM.S.
dc.degree.programMS-Data Science
dc.description.abstractThe recently developed Segment Anything Model has made grabbing semantically meaningful regions of an image easier than before. This will allow for new applications that build on this approach that weren’t previously possible. This thesis investigates integrating the Segment Anything Model with style transfer. Specifically, it proposes Partial Convolution as a way to improve style transfer for segmented regions. Additionally, it investigates how different style transfer techniques are affected by different mask sizes, image statistics, etc.
dc.etdauthor.orcid0009-0004-3655-8732
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/10342/13838
dc.language.isoEnglish
dc.publisherEast Carolina University
dc.subjectComputer Science
dc.titleANALYZING STYLE TRANSFER ALGORITHMS FOR SEGMENTED IMAGES
dc.typeMaster's Thesis
dc.type.materialtext

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
1613427332\1733514312842-SEYED-PRIMARY-2024.pdf
Size:
15.3 MB
Format:
Adobe Portable Document Format