An improved method of new image decomposition technique: two-dimensional EMD
Weijiang Zhao, Heyong Zhang, Deming Ren, Yanchen Qu · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2009
An improved algorithm of 2-D Empirical Mode Decomposition (EMD) in image processing has been presented. It contains selecting extrema of the pixels and interpolation of them in the course of EMD, A variance phenomenon has been discovered in the interpolation of boundary pixels. Delaunay Triangulation has been used to partition the selected extrema, a pixel that not contained in the Delaunay polygon can be processed through symmetry principle, It can restrain the variance phenomenon that appeared in the cubic spline interpolation. An image has been processed with the improved algorithm, The calculation result of standard deviation between the original image and the reconstructed image is 6.667×10-6 . A slight fluctuation can be seen from the calculation result. The reconstructed image is consistent with the original image. It demonstrates that the improved algorithm been presented is accurate and feasible. The method of EMD is used in image compression and de-noising more and more popular, therefore, the improved algorithm in the paper will be useful in the course of calculation speed enhancement of image processing based on EMD.