Hong‐jun Li, Zhi‐min Zhao and Xiao‐lei Yu
The traditional total variation (TV) models in wavelet domain use thresholding directly in coefficients selection and show that Gibbs' phenomenon exists. However, the nonzero…
Abstract
Purpose
The traditional total variation (TV) models in wavelet domain use thresholding directly in coefficients selection and show that Gibbs' phenomenon exists. However, the nonzero coefficient index set selected by hard thresholding techniques may not be the best choice to obtain the least oscillatory reconstructions near edges. This paper aims to propose an image denoising method based on TV and grey theory in the wavelet domain to solve the defect of traditional methods.
Design/methodology/approach
In this paper, the authors divide wavelet into two parts: low frequency area and high frequency area; in different areas different methods are used. They apply grey theory in wavelet coefficient selection. The new algorithm gives a new method of wavelet coefficient selection, solves the nonzero coefficients sort, and achieves a good image denoising result while reducing the phenomenon of “Gibbs.”
Findings
The results show that the method proposed in this paper can distinguish between the information of image and noise accurately and also reduce the Gibbs artifacts. From the comparisons, the model proposed preserves the important information of the image very well and shows very good performance.
Originality/value
The proposed image denoising model introducing grey relation analysis in the wavelet coefficients selecting and modifying is original. The proposed model provides a viable tool to engineers for processing the image.