一种基于分数阶变分的乘性噪声图像去噪模型

A multiplicative fractional-order variation based on noise removal model

经典变分模型在去除乘性噪声的同时会产生纹理细节信息丢失现象。为解决这一问题,将分数阶变分模型与经典的TV模型相结合提出一种新的分数阶变分去噪模型,并利用梯度下降法求解该模型,数值实验表明:该模型较经典的去噪模型在去噪的同时可很好地保持图像边缘和纹理信息,同时对阶梯效应也有所抑制。

A new fraction-order variational model combined with TV model is proposed to solve the problem that the staircase effect and lossing texture details based on the classical variational models for multiplicative noise removal. By using the gradient descent method to solve it, the numerical experimental results show that the proposed model can not only remove noise effectively but also preserve edges, keep the texture and other details as well. At the same time, the staircase effect can be suppressed and the signal- to-noise ratio of the image can be improved.