Categorical Image Quality (CSIQ) Database

Author: Oklahoma State University

Partner: No




Subjective scores: true

Total: 866

SRC: 30

HRC: 29

Ratings: 35

Method: Custom


The Image Coding and Analysis Lab at the Oklahoma State University offers Categorical Image Quality (CSIQ) Database. This database consists of 30 original images. Each original image in the database is distorted using six different types of distortions at four to five different levels of distortion. The distortions used in CSIQ are: JPEG compression, JPEG-2000 compression, global contrast decrements, additive pink Gaussian noise, and Gaussian blurring. This result in 866 distorted versions of original images.


ZIP archives, no password. Links: Subjective rating: Distorted images: Original images:

Broken link!

The original link was:

References and Citation

  • LC10: E. C. Larson and D. M. Chandler, "Most apparent distortion: full-reference image quality assessment and the role of strategy," Journal of Electronic Imaging, 19 (1), March 2010.