HIGH DYNAMIC RANGE IMAGE PROCESSING USING MANIFOLD-BASED ORDERING - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

HIGH DYNAMIC RANGE IMAGE PROCESSING USING MANIFOLD-BASED ORDERING

Résumé

Very few research works have addressed the problem of directly manipulating raw HDR vectors for general HDR image processing. In this paper a framework is proposed towards this aim and is based on a new representation of HDR images in the form of an ordering of vectors and an index image. This enables to formulate vector-preserving image processing methods dedicated to HDR images. The ordering relies on three steps: dictionary learning, manifold learning, and out of sample extension. The performance of the proposed approach is illustrated with innovative examples of HDR image filtering and enhancement.
Fichier principal
Vignette du fichier
Lezoray_ICPR2016_VF.pdf (1.68 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01411026 , version 1 (06-12-2016)

Identifiants

  • HAL Id : hal-01411026 , version 1

Citer

Olivier Lézoray. HIGH DYNAMIC RANGE IMAGE PROCESSING USING MANIFOLD-BASED ORDERING. International Conference on Pattern Recognition, Dec 2016, Cancun, Mexico. ⟨hal-01411026⟩
122 Consultations
275 Téléchargements

Partager

Gmail Facebook X LinkedIn More