Quality assessment of stereoscopic 3 d image compression by binocular integration behaviors

QUALITY ASSESSMENT OF STEREOSCOPIC 3D IMAGE
COMPRESSION BY BINOCULAR INTEGRATION BEHAVIORS
ABSTRACT
The objective approaches of 3D image quality assessment play a key role for the
development of compression standards and various 3D multimedia applications.
The quality assessment of 3D images faces more new challenges, such as asymmetric
stereo compression, depth perception, and virtual view synthesis, than its 2D counterparts. In
addition, the widely used 2D image quality metrics (e.g., PSNR and SSIM) cannot be directly
applied to deal with these newly introduced challenges.
This statement can be verified by the low correlation between the computed objective
measures and the subjectively measured mean opinion scores (MOSs), when 3D images are the
tested targets. In order to meet these newly introduced challenges, in this paper, besides
traditional 2D image metrics, the binocular integration behaviors—the binocular combination
and the binocular frequency integration, are utilized as the bases for measuring the quality of
stereoscopic 3D images.
The effectiveness of the proposed metrics is verified by conducting subjective evaluations
on publicly available stereoscopic image databases. Experimental results show that significant
consistency could be reached between the measured MOS and the proposed metrics, in which the
correlation coefficient between them can go up to 0.88.
Furthermore, we found that the proposed metrics can also address the quality assessment
of the synthesized color-plus depth 3D images well. Therefore, it is our belief that the binocular
integration behaviors are important factors in the development of objective quality assessment
for 3D images.

ARCHITECTURE
EXISTING SYSTEM
Image quality assessment IQA provides the ultimate perceptual quality evaluation; the
associated high cost and complexity handicap its value in real applications. In order to address
this issue, computational objective IQA has long been an active research area since the last
decade. The booming up of 3D movies and the advances in display devices, 3D image is
becoming the new research target for IQA. The quality assessment of anaglyph 3D images was
addressed in and the work dealt with the quality assessment of multi-camera applications (e.g.
panorama images). One direct arisen question is the applicability of existing 2D objective
metrics to the 3D images.
The existing 2D quality assessment metrics can predict well for the Symmetric-Stereo
compression, however, the prediction results are not well addressed for the Asymmetric

counterpart by the same metrics. This work aims to fill-up this gap by proposing a quality
assessment metric which is applicable to both the Symmetric-Stereo and the Asymmetric-Stereo
compressions.
PROPOSED SYSTEM
There are numerous physiological discoveries of binocular vision where we focus on the
binocular visual behaviors that describe the visual inputs integration process. For simplicity,
these physiological discoveries of binocular vision are denoted as binocular integration behaviors
which consist of binocular combination and binocular frequency integration behaviors. In order
to overcome the challenges of 3D image IQA, we integrate the binocular integration behaviors
into the existing 2D objective metrics for evaluating the quality of 3D images. We denote the
integrated quality assessment metrics as the Frequency-Integrated metrics
The new challenges of 3D IQA come mainly from the interactions between the two eyes,
a better understanding of the physiological studies of binocular vision is beneficial to the
development of effective computational models for 3D images. We briefly revisit the findings of
binocular vision.
Modules
1. Pathways of Binocular Visual System
There are two visual pathways for neural processing of visual information in
visual cortex,
Dorsal stream and ventral stream
· Dorsal stream (“Where” pathway) the dorsal stream starts from (primary visual
cortex), goes through area. The functions of dorsal stream are about visual
information guided actions.
· Ventral stream (“What” pathway) the ventral stream begins from area goes
through to area. The perception and recognition visual behaviors occur in ventral
stream.
(1) The visual response of two eyes,

(2) The binocular combination behaviors in the early stage of visual pathway and
(3) The visual information representations and integration.
2. Binocular Combination
In this behaviors of binocular brightness combination when the input brightness is
asymmetric in both eyes (e.g. Fechner’s paradox, cyclopean perception).
Cyclopean perception means that we will have single perceptual image when we
perceive 3D images/videos by two eyes. These behaviors play the role of constraints for
selecting the plausible biological models of binocular combination.
Fechner’s Paradox This binocular combination behavior describes the
phenomenon that a bright light to one eye may appear less bright when a dim light is
shown to the other eye. Cyclopean Perception The cyclopean perception was suggested
as a constraint in the research work [65] for modeling the binocular combination
behavior.
3. Effect of DOG bands
Each quality metric has its own specific visual properties and background
assumptions, a quality metric could not perform well at DOG frequency bands which are
far from the original usages in the regions with zero values and the original usage of VIF
is for natural image only).
The proposed DOG decomposition may be replaced by Gabor filter bank which is
another popular physiological model and the corresponding performance evaluation will
be one of our future works.
SOFTWARE REQUIREMENTS
Hardware Requirements

· System : Pentium IV 2.4 GHz.
· Hard Disk : 80 GB.
· Monitor : 15 VGA Color.
· Mouse : Logitech.
· Ram : 512 MB.
Software Requirements
· Operating system : Windows 8 (32-Bit)
· Front End : Visual Studio 2010
· Coding Language : C#.NET

Quality assessment of stereoscopic 3 d image compression by binocular integration behaviors

More Related Content

What's hot (17)

Viewers also liked (7)

Similar to Quality assessment of stereoscopic 3 d image compression by binocular integration behaviors (20)

More from Shakas Technologies (20)

Recently uploaded (20)

Quality assessment of stereoscopic 3 d image compression by binocular integration behaviors