光学学报, 2018, 38 (10): 1017002, 网络出版: 2019-05-09
基于分组主成分分析的光学相干图像降斑算法 下载: 948次
Optical Coherent Image Despeckling Algorithm Based on Grouping Principal Component Analysis
图像处理 光学相干成像 斑点噪声 主成分分析 块相似 image processing optical coherent image speckle noise principal component analysis block similarity
摘要
通过分析临床医学图像中光学相干断层成像(OCT)的相干斑噪声模型,提出了一种基于局部分组主成分分析的光学相干断层图像降斑算法。根据相干图像的统计特征,利用同态滤波将乘性噪声转换为加性噪声;将训练集中待处理的像素及其邻域表示成子块向量,利用块相似性度量对子块进行分组,并用于主成分分析。为有效抑制相干图像中病灶的噪声干扰,将该算法执行两次。实验结果表明:所提算法在降斑的同时较好地保留了图像的细节信息,而且获得了较高的客观评价指标。
Abstract
By analyzing a speckle noise model of optical coherence tomography (OCT) in clinical medical imaging,we propose a despeckling method for OCT images based on the local grouping principal component analysis. On the basis of the statistical characteristics of coherent images, the multiplicative noise is converted into additive noise by homomorphic filtering. By modeling pixel to be processed in the training set and its neighborhoods as a vector, we group the vectors based on the block similarity measure. Then, the principal component analysis is performed. Considering the noise interference in coherent images with the lesion, we perform the algorithm twice. Experimental results show that the proposed algorithm has better results in terms of speckle noise reduction as well as detail preservation, and satisfying objective evaluation index.
方敬, 滕树云, 牛四杰, 李登旺. 基于分组主成分分析的光学相干图像降斑算法[J]. 光学学报, 2018, 38(10): 1017002. Jing Fang, Shuyun Teng, Sijie Niu, Dengwang Li. Optical Coherent Image Despeckling Algorithm Based on Grouping Principal Component Analysis[J]. Acta Optica Sinica, 2018, 38(10): 1017002.