Image quality assessmentmethod based on nonlinear feature extraction in kernel space

2016, Volume 17, Issue 10

Abstract

Keywords

Related Research

Frontiers of Information Technology & Electronic Engineering >> 2016, Volume 17, Issue 10 doi: 10.1631/FITEE.1500439

Image quality assessmentmethod based on nonlinear feature extraction in kernel space

Institute of VLSI Design, Zhejiang University, Hangzhou 310027, China

Available online: 2016-11-04

HTML17 PDF 3 Collect 0

Next Previous

Abstract

To match human perception, extracting perceptual features effectively plays an important role in image quality assessment. In contrast to most existing methods that use linear transformations or models to represent images, we employ a complex mathematical expression of high dimensionality to reveal the statistical characteristics of the images. Furthermore, by introducing kernel methods to transform the linear problem into a nonlinear one, a full-reference image quality assessment method is proposed based on high-dimensional nonlinear feature extraction. Experiments on the LIVE, TID2008, and CSIQ databases demonstrate that nonlinear features offer competitive performance for image inherent quality representation and the proposed method achieves a promising performance that is consistent with human subjective evaluation.

Keywords

Image quality assessment ; Full-reference method ; Feature extraction ; Kernel space ; Support vector regression

Related Research