Nearest-neighbor based metric functions for indoor scene recognition

Simple item page
buir.advisorGüdükbay, Uğur
dc.contributor.authorÇakır, Fatih
dc.date.accessioned2016-01-08T18:15:28Z
dc.date.available2016-01-08T18:15:28Z
dc.date.issued2011
dc.descriptionAnkara : The Department of Computer Engineering and the Graduate School of Engineering and Science of Bilkent University, 2011.en_US
dc.descriptionThesis (Master's) -- Bilkent University, 2011.en_US
dc.descriptionIncludes bibliographical references leaves 39-44.en_US
dc.description.abstractIndoor scene recognition is a challenging problem in the classical scene recognition domain due to the severe intra-class variations and inter-class similarities of man-made indoor structures. State-of-the-art scene recognition techniques such as capturing holistic representations of an image demonstrate low performance on indoor scenes. Other methods that introduce intermediate steps such as identifying objects and associating them with scenes have the handicap of successfully localizing and recognizing the objects in a highly cluttered and sophisticated environment. We propose a classi cation method that can handle such di culties of the problem domain by employing a metric function based on the nearest-neighbor classi cation procedure using the bag-of-visual words scheme, the so-called codebooks. Considering the codebook construction as a Voronoi tessellation of the feature space, we have observed that, given an image, a learned weighted distance of the extracted feature vectors to the center of the Voronoi cells gives a strong indication of the image's category. Our method outperforms state-of-the-art approaches on an indoor scene recognition benchmark and achieves competitive results on a general scene dataset, using a single type of descriptor. In this study although our primary focus is indoor scene categorization, we also employ the proposed metric function to create a baseline implementation for the auto-annotation problem. With the growing amount of digital media, the problem of auto-annotating images with semantic labels has received signi cant interest from researches in the last decade. Traditional approaches where such content is manually tagged has been found to be too tedious and a time-consuming process. Hence, succesfully labeling images with keywords describing the semantics is a crucial task yet to be accomplished.en_US
dc.description.provenanceMade available in DSpace on 2016-01-08T18:15:28Z (GMT). No. of bitstreams: 1 0005087.pdf: 11460191 bytes, checksum: d559c9127871277bed9fddf88781717a (MD5)en
dc.description.statementofresponsibilityÇakır, Fatihen_US
dc.format.extentxiii, 44 leaves, ilustrations, graphsen_US
dc.identifier.urihttp://hdl.handle.net/11693/15242
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectscene classi cationen_US
dc.subjectindoor scene recognitionen_US
dc.subjectnearest neighbor classi- eren_US
dc.subjectbag-of-visual wordsen_US
dc.subjectimage auto-annotationen_US
dc.subject.lccTA1634 .C35 2011en_US
dc.subject.lcshComputer vision.en_US
dc.subject.lcshImage processing--Digital techniques.en_US
dc.subject.lcshSignal processing--Digital techniques.en_US
dc.subject.lcshPattern recognition systems.en_US
dc.titleNearest-neighbor based metric functions for indoor scene recognitionen_US
dc.typeThesisen_US
thesis.degree.disciplineComputer Engineering
thesis.degree.grantorBilkent University
thesis.degree.levelMaster's
thesis.degree.nameMS (Master of Science)

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0005087.pdf
Size:
10.93 MB
Format:
Adobe Portable Document Format
Download

Collections

Graduate School of Engineering and Science