基于Delaunay三角化的二维无约束优化EMD方法
An unconstrained optimization EMD approach in 2D based on Delaunay triangulation

提出一种改进的基于Delaunay三角化的二维无约束优化经验模态分解(empirical mode decomposition, EMD)方法,对二维图像极值点重新定义,利用对定义的极值点进行Delaunay三角化构建无约束的优化模型对图像进行迭代分解,能够将原始图像自适应分解为尺度从细到粗的内蕴模态图像分量和一个余量。试验结果表明:本研究提出的方法较原始的二维无约束优化EMD方法具有更强的细节获取能力,能够更好地体现原始图像的不同尺度特征。
An improved unconstrained optimization empirical mode decomposition (EMD) approach in two-dimensional (2D) based on Delaunay triangulation was presented. It firstly redefined the extremum of 2D images, and then constructed an optimization model to decompose the input image iteratively based on the Delaunay triangulation of the image extrema. The proposed approach could adaptively decompose the input image into several intrinsic mode images with fine-coarse scales and a residue. Experiment results demonstrated the proposed method had more powerful capabilities in capturing the multi-scale details and image features than the original 2D unconstrained optimization EMD approach.