La vitrine de diffusion des publications et contributions des chercheurs de l'ÉTS
RECHERCHER

Limitations of the SSIM quality metric in the context of diagnostic imaging

Pambrun, Jean-François et Noumeir, Rita. 2015. « Limitations of the SSIM quality metric in the context of diagnostic imaging ». In 2015 IEEE International Conference on Image Processing (ICIP) (Quebec City, QC, Canada, Sept. 27-30, 2015), p. 2960-2963. Piscataway, NJ, USA : IEEE.

[img]
Prévisualisation
PDF
Noumeir R. 2015 12070 Limitations of the SSIM quality metric.pdf - Version acceptée
Licence d'utilisation : Tous les droits réservés aux détenteurs du droit d'auteur.

Télécharger (3MB) | Prévisualisation

Résumé

Lossy image compression is increasingly used in medical applications, but great care must be taken to ensure that no diagnostically relevant features are altered. Guidelines based on compression ratios are often use to mitigate this issue, but are criticized due to the considerable compressibility variations between images. Objective image quality assessment metrics should be used instead, but the most common, mean squared error, is known to be poorly correlated with our perception of quality. Structural similarity (SSIM) is probably currently the most popular alternative, but it is also increasingly criticized. Using computed tomography simulations, this paper shows some of the limitations of SSIM when used with medical images: uniform pooling, distortion underestimation near hard edges, instabilities in regions of low variance and insensitivity in regions high intensities. Furthermore, this paper demonstrates the effect of these limitations when SSIM is used to bound compression in a block coder such as JPEG 2000.

Type de document: Compte rendu de conférence
Professeur:
Professeur
Noumeir, Rita
Affiliation: Génie électrique
Date de dépôt: 13 janv. 2016 19:09
Dernière modification: 15 avr. 2016 15:46
URI: http://espace2.etsmtl.ca/id/eprint/12070

Actions (Authentification requise)

Dernière vérification avant le dépôt Dernière vérification avant le dépôt

Statistiques de téléchargement

Plus de statistiques ...