Visual Perception Based Objective Stereo Image Quality Assessment for 3D Video Communication

Gangyi Jiang,Feng Shao,Zongju Peng,Mei Yu,Xiangyin Mao

doi:10.19026/rjaset.7.606

Abstract

Stereo image quality assessment is a crucial and challenging issue in 3D video communication. One of major difficulties is how to weigh binocular masking effect. In order to establish the assessment mode more in line with the human visual system, Watson model is adopted, which defines visibility threshold under no distortion composed of contrast sensitivity, masking effect and error in this study. As a result, we propose an Objective Stereo Image Quality Assessment method (OSIQA), organically combining a new Left-Right view Image Quality Assessment (LR-IQA) metric and Depth Perception Image Quality Assessment (DP-IQA) metric. The new LR-IQA metric is first given to calculate the changes of perception coefficients in each sub-band utilizing Watson model and human visual system after wavelet decomposition of left and right images in stereo image pair, respectively. Then, a concept of absolute difference map is defined to describe abstract differential value between the left and right view images and the DP-IQA metric is presented to measure structure distortion of the original and distorted abstract difference maps through luminance function, error sensitivity and contrast function. Finally, an OSIQA metric is generated by using multiplicative fitting of the LR-IQA and DP-IQA metrics based on weighting. Experimental results shows that the proposed method are highly correlated with human visual judgments (Mean Opinion Score) and the correlation coefficient and monotony are more than 0.92 under five types of distortions such as Gaussian blur, Gaussian noise, JP2K compression, JPEG compression and H.264 compression.

Highlights

With the rapid development of internet, communication, multimedia technology, applications of 3D video communication technologies will be more extensive nowadays, such as three dimensional television, stereo video conferencing systems and consumer electronics (Fan et al, 2011; Shao et al, 2012; Gotchev et al, 2011)
In consideration of inconformity between human judgments (Mean Opinion Score) and the above proposed metrics and to build an assessment mode which is agreed with the human visual system, we propose a new Objective Stereo Image Quality Assessment (OSIQA) method in this study
Left-Right view Image Quality Assessment (LRIQA) metric based on visual perception: Human Visual System (HVS) is an extremely complex information processing system (Campisi et al, 2007) and it is hard to understand deeply in the limit of many factors

Summary

Introduction

With the rapid development of internet, communication, multimedia technology, applications of 3D video communication technologies will be more extensive nowadays, such as three dimensional television, stereo video conferencing systems and consumer electronics (Fan et al, 2011; Shao et al, 2012; Gotchev et al, 2011). Benoit et al (2008 a, b) proposed SIQA metric based on single view image quality assessment SSIM and C4, which mainly discussed the correlation between subjective perception Technol., 7(14): 2827-2837, 2014 and proposed SIQA under different combination ways of Left-Right view Image Quality Assessment (LRIQA) and Depth Perception Image Quality Assessment (DP-IQA).

Results

Conclusion