A new psychovisual paradigm for image quality assessment: from differentiating distortion types to discriminating qualit
- PDF / 1,731,256 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 83 Downloads / 168 Views
ORIGINAL PAPER
A new psychovisual paradigm for image quality assessment: from differentiating distortion types to discriminating quality conditions Ke Gu · Guangtao Zhai · Xiaokang Yang · Wenjun Zhang
Received: 15 November 2011 / Revised: 18 May 2012 / Accepted: 13 October 2012 / Published online: 16 March 2013 © Springer-Verlag London 2013
Abstract This paper investigates the impacts of image quality level on the prediction accuracy of image quality metrics. While many state-of-the-art perceptual image quality assessment methods have achieved fairly well performances in terms of the correlation between the quality predictions and the subjective scores, none of them took into account the effects of the quality levels of those test images on prediction accuracy of the quality metrics. In this work, inspired by the mechanism of human perception under high- and lowquality conditions, we propose a new image quality assessment paradigm based on image quality level classification. Our investigation on TID2008 and other three publicly available databases (LIVE, CSIQ and Toyama-MICT) results in two valuable findings. First, the performances of major wellknown image quality assessment methods are significantly affected by image quality level. Second, through combining different quality metrics for different quality levels, superior performance can be achieved as compared to some of the best image quality metrics, e.g., SSIM, MS-SSIM, VIF and VIFP. Experiments and comparative studies are provided to confirm the effectiveness of the proposed new paradigm by differentiating quality levels for image quality assessment.
This work was supported in part by NSERC, NSFC (61025005, 60932006, 61001145), SRFDP (20090073110022), postdoctoral foundation of China 20100480603, postdoctoral foundation of Shanghai 11R21414200 and the 111 Project (B07022). K. Gu (B) · G. Zhai · X. Yang · W. Zhang The Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China e-mail: [email protected] K. Gu · G. Zhai · X. Yang · W. Zhang Shanghai Key Laboratory of Digital Media Processing and Transmissions, Shanghai, China
Keywords Image quality assessment (IQA) · Image quality classification · Different perception (DIP) mechanism · Human psychovisual perception · Free energy
1 Introduction Perceptual image quality assessment (IQA) plays an important part in many areas of digital image processing, such as the development and optimization of image compression, storage, transmission and reproduction algorithms. Existing IQA approaches fall into two categories: subjective assessment and objective assessment. Although the subjective assessment approach should be the ultimate quality gauge for images, it is usually time-consuming, expensive and impractical for real-time image processing systems. Therefore, there had been an increased interest in developing objective IQA metrics. According to the availability of reference images to be compared with during the tests, objective IQA methods can be further classifi
Data Loading...
