DocumentCode :
77583
Title :
Objective Consumer Device Photo Quality Evaluation
Author :
Saad, Michele A. ; Corriveau, Philip ; Jaladi, Ramesh
Author_Institution :
Intel Corp., Austin, TX, USA
Volume :
22
Issue :
10
fYear :
2015
fDate :
Oct. 2015
Firstpage :
1516
Lastpage :
1520
Abstract :
We propose an approach to no-reference image quality evaluation that is consumer-centric and targets real consumer-type images with realistic distortions and realistic quality ranges. We show that the state-of-the-art approaches to no-reference image quality assessment do not perform as well on real consumer-type images, and propose an approach which is simple, efficient, easily interpretable, and achieves high prediction performance on a dataset of images with real non-simulated distortions.
Keywords :
image processing; consumer-type images; no-reference image quality evaluation; objective consumer device photo quality evaluation; real consumer-type images; real nonsimulated distortions; realistic distortions; realistic quality ranges; Databases; Discrete cosine transforms; Image quality; Noise measurement; Optical distortion; Predictive models; Quality assessment; Consumer devices; discrete cosine transform; natural scene statistics;
fLanguage :
English
Journal_Title :
Signal Processing Letters, IEEE
Publisher :
ieee
ISSN :
1070-9908
Type :
jour
DOI :
10.1109/LSP.2015.2406861
Filename :
7047738
Link To Document :
بازگشت