期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2012
卷号：46
期号：1
页码：294-302
出版社：Journal of Theoretical and Applied
摘要：Combined with human vision principle, this paper firstly gives the definition of image frequency based on image local gradient and uses it to replace the image gradient in the traditional total variation (TV) model. And then tensor voting principle is introduced into the TV model and a novel texture image denoising method using the combination of tensor voting and total variation minimization is proposed. In the new model an image structure saliency function is given to replace the lagrangian multiplier in TV model, which can adjust the regularizing term and fidelity term according to the different areas of image structure features. Theoretical analysis and numerical experiment show that compared with other existing approaches the new model has an obvious anti-jamming capability and can accurately and subtly describe the sharp edges, feature structures and smooth areas, and can overcome staircase effect and over-smoothing generated by other TV models. Especially for the images with rich texture features and low signal to noise ratio (SNR), it can remove the noise while preserving significant image details and important characteristics and improve the image denoising effect.
