MICT Image Quality Evaluation Database

Due to the advanced development of different image compression techniques and processing systems, there is a very big concern about the levels of image quality both for providers and users in many image processing applications from compression to printing. Obviously, digital images suffer a wide variety of distortion in these applications and perceptual quality of the images are degraded. Therefore, perceptual image quality measurement is an important problem. Consequently Subjective quality assessment is the most accurate method for quality evaluation because it reflects true human perception. Thus, the goal of all objective quality assessment research is to make quality predictions that are in agreement with subjective opinion of human observers.

We conducted subjective experiments to obtain scores from human subjects at MICT lab for a number of images distorted with JPEG and JPEG2000 codec. This data set is available to the research community with free of charge.

If you would download the database, please click following:

toyama_database.zip (140Mbyte).

Please note that if you have any questions, please contact the following:

Prof. Yuukou Horita (Ph.D.) (horita[atmark]eng.u-toyama.ac.jp)
Keiji Shibata (shibata[atmark]eng.u-toyama.ac.jp)
Yoshikazu Kawayoke (kawayoke[atmark]nyoke.com)

Please change the [atmark] into @.


* LIVE Quality Assessment Database
Prof. Alan C. Bovik, The University of Texas at Austin, U.S.A.

* Subjective Quality Assessment IRCCyN/IVC Database
Prof. P. Le Callet, Polytech Nantes/Universite de Nantes, France