Low-complexity computation of visual information fidelity in the discrete wavelet domain

Rezazadeh, Soroosh et Coulombe, Stéphane. 2010. « Low-complexity computation of visual information fidelity in the discrete wavelet domain ». In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (Dallas, USA, March 14-19, 2010) pp. 2438-2441. Piscataway, NJ, USA : Institute of Electrical and Electronics Engineers.
Compte des citations dans Scopus : 5.

Prévisualisation	PDF Coulombe S. 2010 332 Low-complexity computation of visual information fidelity.pdf - Version acceptée Télécharger (199kB) | Prévisualisation
Prévisualisation	PDF Coulombe S. 2010 332 ppt Low-complexity computation of visual.pdf - Présentation Licence d'utilisation : Tous les droits réservés aux détenteurs du droit d'auteur. Télécharger (234kB) | Prévisualisation

Résumé

The visual information fidelity (VIF) index is an objective quality metric that gives very accurate image similarity scores, but at the cost of very high computational complexity. In this paper, a method is presented for calculating VIF in the discrete wavelet domain using the Haar wavelet. The proposed method exploits scalar Gaussian Scale Mixture (GSM) instead of vector GSM for calculating the prediction scores. The complexity of the proposed method is assessed for five different popular image sizes and compared to other methods based on a C/C++ implementation of the algorithms. Experimental results show that the proposed method can compute the visual quality score with less than 30% of the computational complexity of the well-known SSIM index, with greater accuracy than that achieved by the original VIF index method (at about 5% of its computational complexity).

Type de document:	Compte rendu de conférence
Informations complémentaires:	ICASSP 2010
Professeur:	Professeur Coulombe, Stéphane
Affiliation:	Génie logiciel et des technologies de l'information
Date de dépôt:	23 mai 2012 17:55
Dernière modification:	05 juill. 2017 13:39
URI:	https://espace2.etsmtl.ca/id/eprint/332

Actions (Authentification requise)

Dernière vérification avant le dépôt