The application of genetic algorithm based support vector machine for image quality evaluation

Authors:
Li Cui;Song Yun Xie
Affiliations:
Electrical engineering school, Northwestern Polytechnical University, China;Electrical engineering school, Northwestern Polytechnical University, China
Venue:
ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
Year:
2011

Citing 4
Cited 0

The visible differences predictor: an algorithm for the assessment of image fidelity

Digital images and human vision
Image quality assessment: from error visibility to structural similarity

IEEE Transactions on Image Processing
An information fidelity criterion for image quality assessment using natural scene statistics

IEEE Transactions on Image Processing
Image information and visual quality

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we have proposed a novel image quality evaluation algorithm based on the Visual Difference Predictor(VDP), a classical method of estimating the visual similarity between an image under test and its reference one. Compared with state-of-the-art image quality evaluation algorithms, this method have employed a genetic algorithm based support vector machine, instead of linear or nonlinear mathematical models, to describe the relationship between image similarity features and subjective image quality. Subsequent experiments shows that, the proposed method with the state-of-the-art image quality evaluation algorithms the Mean Square Error (MSE), the Structural SImilarity Metric (SSIM), the Multi-scale SSIM (MS-SSIM). Experiments show that VDQM performs much better than its counterparts on both the LIVE and the A57 image databases.