When DR （Digital Radiography） images are filtered, it is necessary to preserve the edges and key details. But the existing methods may inevitably take fine details mistaken for noise to remove. In order to solve the...When DR （Digital Radiography） images are filtered, it is necessary to preserve the edges and key details. But the existing methods may inevitably take fine details mistaken for noise to remove. In order to solve the problem an improved anisotropic diffu- sion filtering model is proposed. Firstly, a novel diffusion function is introduced based on Perona and Malik model, which well overcomes the high rate of convergence. Secondly, the gradient threshold is modified to an adaptive estimation function, so it is bet- ter at adaptive threshold regulations according to the pixels and iteration times. Finally, the edges are extracted from the restored im- ages and the results are evaluated quantificationally. It is shown from the experiments that the proposed method is effective not only in noise reduction but also in details preserved.展开更多
In this paper, we present a new scheme to segment a given image. This scheme utilizes neuro-fuzzy system to derive a proper set of contour pixels based on multi-scale images. We use these fuzzy derivatives to develop ...In this paper, we present a new scheme to segment a given image. This scheme utilizes neuro-fuzzy system to derive a proper set of contour pixels based on multi-scale images. We use these fuzzy derivatives to develop a new curve evolution model. The model automatically detect smooth boundaries, scaling the energy term, and change of topology according to the extracted con- tour pixels set. We present the numerical implementation and the experimental results based on the semi-implicit method. Experi- mental results show that one can obtains a high clualitv edge contour.展开更多
基金Supported by Natural Science Foundation of China(61163047)Natural Science Foundation of Jiangxi Province(20114BAB201036)
文摘When DR （Digital Radiography） images are filtered, it is necessary to preserve the edges and key details. But the existing methods may inevitably take fine details mistaken for noise to remove. In order to solve the problem an improved anisotropic diffu- sion filtering model is proposed. Firstly, a novel diffusion function is introduced based on Perona and Malik model, which well overcomes the high rate of convergence. Secondly, the gradient threshold is modified to an adaptive estimation function, so it is bet- ter at adaptive threshold regulations according to the pixels and iteration times. Finally, the edges are extracted from the restored im- ages and the results are evaluated quantificationally. It is shown from the experiments that the proposed method is effective not only in noise reduction but also in details preserved.
基金Supported by National Science Foundation of China(60403036)National Science Foundation of Shandong Province(Y2003G01)
文摘In this paper, we present a new scheme to segment a given image. This scheme utilizes neuro-fuzzy system to derive a proper set of contour pixels based on multi-scale images. We use these fuzzy derivatives to develop a new curve evolution model. The model automatically detect smooth boundaries, scaling the energy term, and change of topology according to the extracted con- tour pixels set. We present the numerical implementation and the experimental results based on the semi-implicit method. Experi- mental results show that one can obtains a high clualitv edge contour.
