Nearest-neighbor based metric functions for indoor scene recognition

buir.contributor.authorUlusoy, Özgür
buir.contributor.authorGüdükbay, Uğur
dc.citation.epage1492en_US
dc.citation.issueNumber11en_US
dc.citation.spage1483en_US
dc.citation.volumeNumber115en_US
dc.contributor.authorCakir, F.en_US
dc.contributor.authorGüdükbay, Uğuren_US
dc.contributor.authorUlusoy, Özgüren_US
dc.date.accessioned2016-02-08T09:50:25Z
dc.date.available2016-02-08T09:50:25Z
dc.date.issued2011en_US
dc.departmentDepartment of Computer Engineeringen_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 classification method that can handle such difficulties of the problem domain by employing a metric function based on the Nearest-Neighbor classification 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. © 2011 Elsevier Inc. All rights reserved.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T09:50:25Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2011en
dc.identifier.doi10.1016/j.cviu.2011.07.007en_US
dc.identifier.issn1077-3142en_US
dc.identifier.urihttp://hdl.handle.net/11693/21729en_US
dc.language.isoEnglishen_US
dc.publisherAcademic Pressen_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/j.cviu.2011.07.007en_US
dc.source.titleComputer Vision and Image Understandingen_US
dc.subjectBag - of - visual wordsen_US
dc.subjectIndoor scene recognitionen_US
dc.subjectNearest neighbor classifieren_US
dc.subjectScene classificationen_US
dc.subjectClassification methodsen_US
dc.subjectClassification procedureen_US
dc.subjectCodebook constructionsen_US
dc.subjectCodebooksen_US
dc.subjectData setsen_US
dc.subjectDescriptorsen_US
dc.subjectFeature spaceen_US
dc.subjectFeature vectorsen_US
dc.titleNearest-neighbor based metric functions for indoor scene recognitionen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Nearest_Neighbor_based_Metric_Functions_for_indoor_scene_recognition.pdf
Size:
2.31 MB
Format:
Adobe Portable Document Format
Description:
Full printable version