Reduced-reference video quality metric based on edge information
In multimedia transmission, it is important to rely on an objective quality metric which accurately represents the subjective quality of processed images and video sequences. Reduced-reference metrics make use of side-information that is transmitted to the receiver for estimating the quality of...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2018
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/67291/ http://irep.iium.edu.my/67291/ http://irep.iium.edu.my/67291/1/67291_Reduced-reference%20video%20quality%20metric%20based_complete.pdf http://irep.iium.edu.my/67291/2/67291_Reduced-reference%20video%20quality%20metric%20based_scopus.pdf |
| Summary: | In multimedia transmission, it is important to rely
on an objective quality metric which accurately represents the
subjective quality of processed images and video sequences.
Reduced-reference metrics make use of side-information that is
transmitted to the receiver for estimating the quality of the
received sequence with low complexity. In this paper, novel Edgebased
Dissimilarity Reduced-Reference video quality metric
(EDIRR) is proposed. The metric is evaluated by finding the
dissimilarity between the edge information of original and
distorted sequences. The edge degradation can be detected in this
manner as perceived video quality is highly associated with edge
structural. In this paper, the aim is to construct a novel RR video
quality metric based on edge dissimilarity for video quality
assessment. The proposed metric is derived from the motivation
that human perception understands an image mainly according
to its low-level features, specifically the edges, which are a
measure of the significance of a local structure. From the results
obtained, there is a moderate positive correlation between the
proposed metric score with the subjective scores in the overall
observation but with correlation for tested sequences with a
lower DMOS. EDIRR, with LCC of 0.938, outperforms PSNR
and VIFP on wireless distortion induced sequences and the
proposed metric, with LCC of 0.988, performs on a par with
PSNR, SSIM and VIFP for H.264 compressions distortions. |
|---|