Yayın:
Key-frame based video fingerprinting by NMF

Basit öğe sayfası
dc.contributor.authorCirakman, Ozgun
dc.contributor.authorGünsel, Bilge
dc.contributor.authorSengör, Neslihan Serap
dc.contributor.authorGursoy, Ozan
dc.contributor.ituauthorGünsel, Kalyoncu Bilge
dc.contributor.ituauthorŞengör, Neslihan Serap
dc.date.accessioned2026-01-26T05:07:22Z
dc.date.issued2010-09-01
dc.description.abstractThis paper presents a key-frame based video fingerprinting method in which the fingerprint matching is modeled as a two hypothesis testing problem. The perceptual fingerprints that uniquely identify the video content are extracted by non-negative matrix factorization (NMF) via Gaussian weighting in order to assure compactness and robustness to global luminance distortions. The system performance is further improved to enhance its robustness to geometric attacks by integrating the transform invariant NMF (T-NMF) indicies into the matching scheme. The overall performance is evaluated on TRECVID video sequences. It is shown that the proposed video fingerprinting method is highly robust to global attacks described by TRECVID and it can also handle the geometric attacks for the transformations used at indexing phase.
dc.description.urihttps://doi.org/10.1109/icip.2010.5652649
dc.description.urihttps://doi.org/10.1109/ICIP.2010.5652649
dc.description.urihttps://dx.doi.org/10.1109/icip.2010.5652649
dc.identifier.doi10.1109/icip.2010.5652649
dc.identifier.endpage2376
dc.identifier.openairedoi_dedup___::e8667d0214303d42773a305eb3834978
dc.identifier.orcid0000-0003-3628-3316
dc.identifier.orcid0000-0001-6278-2392
dc.identifier.startpage2373
dc.identifier.urihttps://hdl.handle.net/11527/61844
dc.publisherIEEE
dc.relation.ispartof2010 IEEE International Conference on Image Processing
dc.titleKey-frame based video fingerprinting by NMF
dc.typeArticle
dspace.entity.typePublication
person.identifier.orcid0000-0003-3628-3316
person.identifier.orcid0000-0001-6278-2392

Dosyalar

Koleksiyonlar

Yayınlar