Multi-focus multi-source image fusion method

Abstract

The invention provides a multi-focus multi-source image fusion method. The method inclues: carrying out decomposition, fusion and superposition processing on the source image with the M focus points;decomposing the source image into a base part and details; filtering and denoising the base part by adopting an even number complex wavelet algorithm to obtain a fused base part; a pre-training modelVGG-S is adopted to perform depth feature extraction on details to obtain detail features, a multi-layer fusion strategy is adopted to reconstruct the detail features, then a gradient maximum value isselected for the detail features to obtain fusion details, and finally the obtained fusion base part and the fusion details are superposed to complete image fusion. The fusion image obtained by the method not only reserves the feature information of the image before fusion and improves the utilization rate of the effective information of the image, but also has higher definition, and is more detailed, comprehensive and superior. The method is wider in application range and can provide more image information in the aspects of daily life, medicine, military affairs and the like.

Description

technical field [0001] The invention belongs to the field of image fusion, and relates to a multi-focus multi-source image fusion method, in particular to a multi-focus multi-source image fusion method based on deep learning and dual-tree complex wavelet technology. Background technique [0002] With the continuous development of social science and technology, multiple and diverse imaging devices have emerged, such as color photography, color infrared photography, multispectral photography, mobile phone photography, etc. These imaging devices are widely used in various industries. However, due to the photography limitations of each device itself, the photos taken may not necessarily meet the needs. [0003] At present, various technologies are applied in the field of multi-source image fusion. Common image fusion techniques include: wavelet transform, contour transform, sparse representation, etc. [0004] The wavelet transform method can fuse corresponding information in ...

AI Technical Summary

Problems solved by technology

At present, the existing method of using deep learning to fuse images still has great defects. On the one hand, in order to obtain a better fusion effect, it is still necessary to post-process the fused image. On the other hand, this method is only suitable for the fusion of multi-source images. In addition, as the network layer continues to deepen, it is easy to lose some detailed features, resulting in blurred images.

Images