基于非局部相似联合低秩表示的高光谱图像去噪

Hyperspectral Images Denoising Based on Non-local Similarity Joint Low-rank Representation

高光谱图像(Hyperspectral Images,HSI)在采集过程中常受到多种类型的噪声干扰,会直接影响其在后续应用中的精度,因此HSI的去噪是一项十分重要的预处理过程。低秩表示(Low-Rank Representation,LRR)模型能很好地满足HSI的光谱性质,但该框架下字典的选择尤为重要,在当下仍是一个开放性的问题。同时,典型去噪方法仅考虑了图像的局部相关性,已不能满足去噪要求,非局部相似性在图像中也是不可忽略的。基于LRR,文中提出了一种新的HSI去噪算法。首先,综合考虑噪声的类型,选取具有更全面的噪声判别能力的字典;其次,在对图像分块处理的前提下,通过聚类的方式引入非局部相似信息,将相似的图像块联合起来进行低秩表示。在模拟Indian Pines数据集以及EO-1 Hyperion真实数据集上的实验结果均表明,相较于目前主流的HSI去噪方法,无论是在图像的目视效果还是在模拟数据集的定量评价指标下,所提方法均有显著提升。

The acquisition of hyperspectral images(HSI)is often interfered by multiple types of noise,which will directly affect accuracy in the subsequent applications.Therefore,HSI denoising is a very important pretreatment process.The low-rank representation(LRR)model can well satisfy the spectral properties of HSI.However,the choice of dictionary under this framework is particularly significant,which is still an open question at present.Meanwhile,the typical method can’t satisfy the requirement well by only considering the local correlation of the image,and the non-local similarity is equally of significance.Based on LRR,a new method of HSI denoising was proposed.Firstly,the type of noise is considered comprehensively and the dictionary with more comprehensive discrimination ability is selected.Secondly,on the premise of block processing,non-local similar information is introduced through clustering,and similar blocks are combined for LRR framework.The experimental results on the simulated In-dian Pines and real EO-1 Hyperion data set show that the proposed method performs better than the state-of-art HSI denosing methods both in the visual effect of the image and the quantitative evaluation index of the simulated data set.