提出一种低秩稀疏成分分解和显著性相结合的医学图像融合方法。所提方法假设待融合源图像由低秩成分和稀疏成分构成, 设计了低秩与稀疏成分分解模型, 通过不同的字典对不同成分进行了稀疏表达。在融合过程中采用一种“绝对值”取大的策略对低秩成分融合, 以保留源图像的亮度信息;对于稀疏成分, 提出一种基于视觉显著性度量的方法来保留显著性特征。实验结果表明,本文方法无论从主观视觉还是客观评价指标上都优于最新的方法。

The combination of sparse low rank decomposition and salience of medical image fusion method are proposed. This approach hypothesis that the source image of preparing fusion is composed of low rank components and sparse components, so the low rank and sparse composition of decomposition model is designed, and is sparse expressed throwing different dictionaries on different ingredients. In order to retain source image of brightness information, an 'absolute' taking big strategy for low rank ingredients is adopted in the fusion process. For the sparse component, a new visual salience measures method is presented to preserve salience characteristics. Experimental results demonstrate that the proposed approach outperforms state-of-the- art fusion methods in both visual effects and quantitative assessments.