Kernel likelihood estimation for superpixel image parsing

Basit Öğe Kaydı
dc.authorid0000-0002-6842-1528
dc.contributor.authorAteş, Hasan Fehmien_US
dc.contributor.authorSünetci, Sercanen_US
dc.contributor.authorAk, Kenan Emiren_US
dc.date.accessioned2016-10-24T21:23:30Z
dc.date.available2016-10-24T21:23:30Z
dc.date.issued2016
dc.departmentIşık Üniversitesi, Mühendislik Fakültesi, Elektrik-Elektronik Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering, Department of Electrical-Electronics Engineeringen_US
dc.description.abstractIn superpixel-based image parsing, the image is first segmented into visually consistent small regions, i.e. superpixels; then superpixels are parsed into different categories. SuperParsing algorithm provides an elegant nonparametric solution to this problem without any need for classifier training. Superpixels are labeled based on the likelihood ratios that are computed from class conditional density estimates of feature vectors. In this paper, local kernel density estimation is proposed to improve the estimation of likelihood ratios and hence the labeling accuracy. By optimizing kernel bandwidths for each feature vector, feature densities are better estimated especially when the set of training samples is sparse. The proposed method is tested on the SIFT Flow dataset consisting of 2,688 images and 33 labels, and is shown to outperform SuperParsing and some of its extended versions in terms of classification accuracy.en_US
dc.description.versionPublisher's Versionen_US
dc.identifier.citationAteş, H. F., Sünetci, S. & Ak, K. E. (2016). Kernel likelihood estimation for superpixel image parsing. Paper presented at the Lecture Notes in Computer Science, 9730, 234-242. doi:10.1007/978-3-319-41501-7_27en_US
dc.identifier.doi10.1007/978-3-319-41501-7_27
dc.identifier.endpage242
dc.identifier.isbn9783319415000
dc.identifier.isbn9783319415017
dc.identifier.issn0302-9743
dc.identifier.issn1611-3349
dc.identifier.scopus2-s2.0-84978805298
dc.identifier.scopusqualityQ3
dc.identifier.startpage234
dc.identifier.urihttps://hdl.handle.net/11729/1138
dc.identifier.urihttp://dx.doi.org/10.1007/978-3-319-41501-7_27
dc.identifier.volume9730
dc.identifier.wosWOS:000386604000027
dc.identifier.wosqualityQ4
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakConference Proceedings Citation Index – Science (CPCI-S)en_US
dc.institutionauthorAteş, Hasan Fehmien_US
dc.institutionauthorSünetci, Sercanen_US
dc.institutionauthorAk, Kenan Emiren_US
dc.institutionauthorid0000-0002-6842-1528
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherSpringer Verlagen_US
dc.relation.ispartofLecture Notes in Computer Scienceen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectImage parsingen_US
dc.subjectImage segmentationen_US
dc.subjectKernel density estimationen_US
dc.subjectSuperpixelen_US
dc.subjectClassification (of information)en_US
dc.subjectImage analysisen_US
dc.subjectImage processingen_US
dc.subjectPixelsen_US
dc.subjectStatisticsen_US
dc.subjectClassification accuracyen_US
dc.subjectClassifier trainingen_US
dc.subjectConditional densityen_US
dc.subjectLabeling accuraciesen_US
dc.subjectLikelihood estimationen_US
dc.subjectSuper pixelsen_US
dc.titleKernel likelihood estimation for superpixel image parsingen_US
dc.typeConference Objecten_US
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
1138.pdf
Boyut:
1.06 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Publisher's Version
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.71 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bildiri Koleksiyonu | Elektrik-Elektronik Mühendisliği Bölümü
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu