Learning-Based Satisfied User Ratio Prediction for Symmetrically and Asymmetrically Compressed Stereoscopic Images

The satisfied user ratio (SUR) for a given distortion level is the fraction of subjects that cannot perceive a quality difference between the original image and its compressed version. By predicting the SUR, one can determine the highest distortion level which allows to save bit rate while guarantee...

Full description

Saved in:
Bibliographic Details
Published in:IEEE multimedia 2021-07, Vol.28 (3), p.8-20
Main Authors: Fan, Chunling, Zhang, Yun, Hamzaoui, Raouf, Ziou, Djemel, Jiang, Qingshan
Format: Magazinearticle
Language:English
Subjects:
asymmetric stereoscopic compression
Asymmetry
Binocular vision
Decision trees
Distortion
Feature extraction
Image coding
Image quality
picture-level just noticeable difference
Predictive models
Regression models
Regression tree analysis
satisfied user ratio
Stereo image processing
stereoscopic image quality assessment
Stereoscopy
symmetric stereoscopic compression
Transform coding
Two dimensional displays
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The satisfied user ratio (SUR) for a given distortion level is the fraction of subjects that cannot perceive a quality difference between the original image and its compressed version. By predicting the SUR, one can determine the highest distortion level which allows to save bit rate while guaranteeing a good visual quality. We propose the first method to predict the SUR for symmetrically and asymmetrically compressed stereoscopic images. Unlike SUR prediction techniques for two-dimensional images and videos, our method exploits the properties of binocular vision. We first extract features that characterize image quality and image content. Then, we use gradient boosting decision trees to reduce the number of features and train a regression model that learns a mapping function from the features to the SUR values. Experimental results on the SIAT-JSSI and SIAT-JASI datasets show high SUR prediction accuracy for H.265 All-Intra and JPEG2000 symmetrically and asymmetrically compressed stereoscopic images.
ISSN:1070-986X
1941-0166
DOI:10.1109/MMUL.2021.3060831