%0 Journal Article
%T 基于深度先验的乘性噪声图像去噪<br>Multiplicative Noise Image Denoising Based on Deep Image Prior
%A 李都
%A 杜卫家
%A 王恩泽
%A 韩东
%A 李加健
%A 许建楼
%J Advances in Applied Mathematics
%P 2227-2234
%@ 2324-8009
%D 2023
%I Hans Publishing
%R 10.12677/AAM.2023.125228
%X 深度图像先验作为典型的无监督学习方法，不需要采用大量的训练样本，因此在一些难以采集大量训练样本训练数据集的领域有许多应用前景，另外，采集大量训练样本需要耗费大量的人力物力，并且可能出现模型的过拟合问题。在本文中，为了有效地去除图像中的乘性噪声，提出了一种基于深度先验的图像去噪变分模型。为求解新模型，本文采用交替方向法求解该问题。数值实验表明，相比其它先进的方法，本文的模型取得更好的去噪结果，具有更好的图像视觉效果。<br />
As a typical unsupervised learning method, deep image prior does not require a large number of training samples, so it has many application prospects in some fields where it is difficult to collect a large number of training samples and training data sets. In addition, collecting a large number of training samples requires a lot of manpower and material resources, and the problem of overfitting of the model may occur (and the model may be over-fitted). In this paper, to effectively remove multiplicative noise in images, a deep prior-based variational model for image denoising is pro-posed. To solve the new model, this paper adopts the alternating direction method to solve the problem. Numerical experiments show that the proposed model in this paper can remove multipli-cative noise more effectively than other state-of-the-art methods, and has better image visual ef-fects.
%K 图像去噪，神经网络，乘性噪声，交替方向法，深度图像先验<br>Image Denoising
%K Neural Network
%K Multiplicative Noise
%K Alternating Direction Method
%K Depth Image Prior
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=65665