Image Processing Based On Modified BEMD Method

The empirical mode decomposition (EMD) introduced by Huang is a new method in signal processing. It is suitable for non-stationary signal processing. The empirical mode decomposition, which is independent of Fourier transform, is a fully data driven method with multiscale features. Recently, it is widely used in many fields, such as signal denoising, engineering fault diagnosis and independent component analysis.Since the EMD method has good effects in one-dimensional signal processing, scholars extend it to bidimensional. They introduce some bidimensional empirical mode decomposition (BEMD) methods, and process bidimensional signal with these BEMD. Because of the complexity in bidimensional signal, the general BEMD have many defects need to improve.In this thesis, we improve the BEMD method which is introduced by J. C. Nunes et al. Our approach has good effects in texture segmentation, image denoising and image decomposition without parameter. The modified BEMD method in this thesis is introduced to process high resolution images. The image is split into several blocks, and every block is processed individually. So we can get ride of solving large linear equations and calculating huge matrix, and the time and space complexity are lowered greatly. It is proved that the modified method has high a calculating speed and need few memory space.