Comparison of Image Quality Assessment Algorithms on Compressed Images

Christophe Charrier (1) , Kenneth Knoblauch (2) , Anush K. Moorthy (3) , Alan C. Bovik (3) , Laurence T. Maloney (4)

1 Equipe Image - Laboratoire GREYC - UMR6072
2 SBRI - Institut cellule souche et cerveau
3 LIVE
4 Department of Psychology, Center for Neural Science

A crucial step in image compression is the evaluation of its performance, and more precisely the available way to measure the nal quality of the compressed image. Usually, to measure performance, some measure of the covariation between the subjective ratings and the degree of compression is performed between rated image quality and algorithm. Nevertheless, local variations are not well taken into account.We use the recently introduced Maximum Likelihood Di erence Scaling (MLDS) method to quantify supra-threshold perceptual di erences between pairs of images and examine how perceived image quality estimated through MLDS changes the compression rate is increased. This approach circumvents the limitations inherent to subjective rating methods.

Mots clés: Maximum-Likelihood difference scaling; quality assessment

Domaines: Traitement des images [eess.IV]

Christophe Charrier, Kenneth Knoblauch, Anush K. Moorthy, Alan C. Bovik, Laurence T. Maloney. Comparison of Image Quality Assessment Algorithms on Compressed Images. SPIE,Image Quality and System Performance VII, Jan 2010, United States. pp.75290B-1 - 75290B-11, ⟨10.1117/12.840221⟩. ⟨hal-00808402⟩