A multi-focus image fusion method based on 2D emd and improved local energy

Abstract

The invention relates to a multi-focus image fusion method based on two-dimensional EMD and improved local energy. Firstly two-dimensional EMD decomposition is carried out on source images, then a method with the combination of a maximum criterion and a weighted average fusion rule based on the improved local energy is employed to process an intrinsic mode function (IMF) component corresponding to the fusion image on the corresponding frequency band. After the two-dimensional EMD decomposition of two corresponding source images, when IMF component phase positions are the same, a local energy maximum criterion is employed by the IMF component corresponding to a fused image. When the phase positions are opposite, the IMF component corresponding to the fused image is determined by using a local energy weighted average method. A disadvantage that the consideration of independent information contained in each pixel in a window is insufficient by a traditional fusion method is overcome by a fusion rule. Finally, a fusion result is obtained through carrying out two-dimensional EMD inverse transformation on a fusion component. Thus the two-dimensional EMD and the improved local energy are combined, the quality of the fused image can be greatly improved, and the method has important significance and use value for the subsequent processing and image display of an application system.

Description

technical field [0001] The invention belongs to a digital image processing method, relates to a multi-focus image fusion method and the field of data information fusion, in particular to a multi-focus image fusion method based on two-dimensional EMD and improved local energy, which can be applied to various military or civilian multi-focus Image fusion system. Background technique [0002] Multi-focus image fusion means that multiple images formed due to different lens focus are processed to obtain a result image with clear target focus. [0003] At present, the commonly used multi-focus image fusion methods are mainly based on wavelet transform or higher level wavelet algorithm. Although the wavelet-based image fusion algorithm can decompose the image very well and get a good fusion result, the wavelet basis function [1] It has always been a difficult problem. Moreover, the image fusion based on wavelet transform is to fuse the local features of each pixel or small area,...

AI Technical Summary

Problems solved by technology

Since the change of the absolute intensity of the image signal can be reflected by the local energy, and the points with large changes in the image signal intensity reflect the salient features of the image, but this rule has the disadvantage of insufficient consideration of the independent information contained in each pixel in the window

Images