Crowdsourced study of subjective image quality

Author

Ghadiyaram, Deepti ; Bovik, Alan C.

Author_Institution

Lab. of Image & Vide o Eng. (LIVE), Univ. of Texas at Austin, Austin, TX, USA

fYear

2014

Firstpage

84

Lastpage

88

Abstract

We designed and created a new image quality database that models diverse authentic image distortions and artifacts that affect images that are captured using modern mobile devices. We also designed and implemented a new online crowdsourcing system, which we are using to conduct a very large-scale, on-going, multi-month image quality assessment (IQA) subjective study, wherein a wide range of diverse observers record their judgments of image quality. Our database currently consists of over 320,000 opinion scores on 1,163 authentically distorted images evaluated by over 7000 human observers. The new database will soon be made freely available for download and we envision that the fruits of our efforts will provide researchers with a valuable tool to benchmark and improve the performance of objective IQA algorithms.

Keywords

image capture; visual databases; IQA algorithms; IQA subjective study; authentically distorted images; diverse authentic image distortions; human observers; image capture; large-scale on-going multimonth image quality assessment subjective study; mobile devices; opinion scores; subjective image quality database; Crowdsourcing; Databases; Image quality; Quality assessment; Standards; Video recording; Visualization; crowd-sourcing; human study; image quality; quality assessment;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 2014 48th Asilomar Conference on

Print_ISBN

978-1-4799-8295-0

Type

conf

DOI

10.1109/ACSSC.2014.7094402

Filename

7094402