基于变分的保持特征的有噪图像放大算法

Feature Preserving Noisy Image Magnification Based on a Variation Model

针对图像放大后出现边缘模糊的现象,该文考察了典型边缘的特征,利用整体变分思想,提出了一种基于变分模型的有噪图像放大算法。利用导出的偏微分方程和图像边缘的局部梯度信息,该文算法实施一种自适应非线性滤波处理,能够较好地保持图像边缘锐度,同时有效地去除图像噪声。为了保持图像的特征和细节,文章利用图像的方向导数局部地调整正则系数.理论分析和实验结果皆表明此文算法的有效性。

To deblur edges after image magnification,an edge sharpness preserving noisy image magnification simultaneously denoising effectively is put forward,which adopts the idea of total variation model,after having reviewing the character of a typical edge.Utilizing the deduced partial differential equation and local gradients of edges,our algorithm implements an adoptive nonlinear filter process.To preserve image features and fine part,the regular coefficient is locally adjusted according to the directional derivatives of the image.Both theoretical analysis and experiments have verified the efficiency of our algorithm in this paper.