Revisiting the Regression between Raw Outputs of Image Quality Metrics and Ground Truth Measurements

Chanho JUNG  Sanghyun JOO  Do-Won NAM  Wonjun KIM  

IEICE TRANSACTIONS on Information and Systems   Vol.E99-D   No.11   pp.2778-2787
Publication Date: 2016/11/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2015EDP7099
Type of Manuscript: PAPER
Category: Image Processing and Video Processing
machine learning,  image quality assessment (IQA),  image quality metric (IQM),  DMOS,  human visual system,  

Full Text: PDF(4.4MB)
>>Buy this Article

In this paper, we aim to investigate the potential usefulness of machine learning in image quality assessment (IQA). Most previous studies have focused on designing effective image quality metrics (IQMs), and significant advances have been made in the development of IQMs over the last decade. Here, our goal is to improve prediction outcomes of “any” given image quality metric. We call this the “IQM's Outcome Improvement” problem, in order to distinguish the proposed approach from the existing IQA approaches. We propose a method that focuses on the underlying IQM and improves its prediction results by using machine learning techniques. Extensive experiments have been conducted on three different publicly available image databases. Particularly, through both 1) in-database and 2) cross-database validations, the generality and technological feasibility (in real-world applications) of our machine-learning-based algorithm have been evaluated. Our results demonstrate that the proposed framework improves prediction outcomes of various existing commonly used IQMs (e.g., MSE, PSNR, SSIM-based IQMs, etc.) in terms of not only prediction accuracy, but also prediction monotonicity.