In this paper, the problem of de-noising of an image contaminated with
Additive White Gaussian Noise (AWGN) is studied. This subject is an open
problem in signal processing for more than 50 years. Local methods suggested in
recent years, have obtained better results than global methods. However by more
intelligent training in such a way that first, important data is more effective
for training, second, clustering in such way that training blocks lie in
low-rank subspaces, we can design a dictionary applicable for image de-noising
and obtain results near the state of the art local methods. In the present
paper, we suggest a method based on global clustering of image constructing
blocks. As the type of clustering plays an important role in clustering-based
de-noising methods, we address two questions about the clustering. The first,
which parts of the data should be considered for clustering? and the second,
what data clustering method is suitable for de-noising.? Then clustering is
exploited to learn an over complete dictionary. By obtaining sparse
decomposition of the noisy image blocks in terms of the dictionary atoms, the
de-noised version is achieved. In addition to our framework, 7 popular
dictionary learning methods are simulated and compared. The results are
compared based on two major factors: (1) de-noising performance and (2)
execution time. Experimental results show that our dictionary learning
framework outperforms its competitors in terms of both factors.

本文针对加性白噪声对图像造成的污染问题，提出并比较了 7 种字典学习方法，并采用全局聚类方法进行图像构建块的聚类去噪，得到了在降噪效果和执行时间两方面皆优的结果。

基于聚类的图像去噪聚类研究

A Study on Clustering for Clustering Based Image De-Noising

We propose a new model, together with advanced optimization, to separate a
thick scattering media layer from a single natural image. It is able to handle
challenging underwater scenes and images taken in fog and sandstorm, both of
which are with significantly reduced visibility. Our method addresses the
critical issue -- this is, originally unnoticeable impurities will be greatly
magnified after removing the scattering media layer -- with transmission-aware
optimization. We introduce non-local structure-aware regularization to properly
constrain transmission estimation without introducing the halo artifacts. A
selective-neighbor criterion is presented to convert the unconventional
constrained optimization problem to an unconstrained one where the latter can
be efficiently solved.

本研究提出了一种新方法及优化策略用于去除自然图像中的散射介质层，特别是在具有挑战性的水下场景、雾霾以及沙尘暴等低可见度环境下，利用非局部结构感知正则化约束了传输估计，并采用选择性邻域标准将非常规约束优化问题转化为无约束问题，最终实现高效分离。

密集散射层去除

Dense Scattering Layer Removal

Neural network has been attracting more and more researchers since the past
decades. The properties, such as parameter sensitivity, random similarity,
learning ability, etc., make it suitable for information protection, such as
data encryption, data authentication, intrusion detection, etc. In this paper,
by investigating neural networks' properties, the low-cost authentication
method based on neural networks is proposed and used to authenticate images or
videos. The authentication method can detect whether the images or videos are
modified maliciously. Firstly, this chapter introduces neural networks'
properties, such as parameter sensitivity, random similarity, diffusion
property, confusion property, one-way property, etc. Secondly, the chapter
gives an introduction to neural network based protection methods. Thirdly, an
image or video authentication scheme based on neural networks is presented, and
its performances, including security, robustness and efficiency, are analyzed.
Finally, conclusions are drawn, and some open issues in this field are
presented.

通过研究神经网络的性质，提出了基于神经网络的低成本身份验证方法，用于身份验证图像或视频，以检测它们是否被恶意修改

基于神经网络的图像认证

Image Authentication Based on Neural Networks

The pixel values of an image can be casted into a real ket of a Hilbert space
using an appropriate block structured addressing. The resulting state can then
be rewritten in terms of its matrix product state representation in such a way
that quantum entanglement corresponds to classical correlations between
different coarse-grained textures. A truncation of the MPS representation is
tantamount to a compression of the original image. The resulting algorithm can
be improved adding a discrete Fourier transform preprocessing and a further
entropic lossless compression.

通过适当的块状结构寻址，图像的像素值可以被投射到希尔伯特空间的实部上，这样产生的状态可以以其矩阵乘积状态表示的方式进行重写，量子纠缠对应于不同粗粒度纹理之间的经典关联，MPS 表示的截断相当于对原始图像的压缩，该算法可通过添加离散傅立叶变换预处理和进一步的熵无损压缩进行改进。