Image fusion processing method, system and computer program based on fuzzy operator

Abstract

The invention belongs to the technical field of image processing, and discloses an image fusion processing method and system based on a fuzzy operator, and a computer program; two images that are fused according to needs, that is, source image 1 and source image 2, are pixelated by a Lukasiewicz implication operator Level learning and training, get the relation matrix R; take the source graph 1 as the input information, take R as the relation matrix, use the Lukasiewicz triangular modulus operator T Lu , to obtain the fused target image. Compared with the existing image fusion method, the present invention saves a lot of complex mathematical calculations and preliminary work, is simple, efficient and easy to implement, and can complement and fuse the image information to be fused well no matter it is brightness information or detail information. The final image has good visual effects, obvious details and clear targets. From the fusion images measured under the same operating environment of the same computer in the following examples, it can be clearly compared that the fusion method of the present invention is superior to the prior art.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image fusion processing method and system based on a fuzzy operator, and a computer program. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: pixel-level fusion is a relatively common method for image fusion. The main pixel-level fusion methods include weighted average method, fusion method based on statistics, pseudo-color image fusion method, fusion method based on artificial neural network, fusion method based on multi-scale analysis, etc. 1) Weighted average method. The weighted average method is the simplest image fusion method. It mainly performs weighted processing on the gray values ​​of corresponding pixels of multiple source images. Two representative weighted average methods are principal component analysis (PCA) method and adaptive weighted average (AWA) method. In the PCA metho...

AI Technical Summary

Problems solved by technology

[0004] (1) The signal-to-noise ratio of the image synthesized by the existing weighted average method is reduced; when the gray level difference of the fused image is relatively large, there will be obvious splicing traces, which is not conducive to human eye recognition and subsequent target recognition process

[0005] (2) The existing image fusion algorithm is complex, and the execution time efficiency is low, which greatly reduces the time efficiency of program execution

[0006] (3) The existing image fusion methods are inseparable from traditional classic mathematical tools, which are too complicated and time-consuming compared with fuzzy logic operations

[0008] Existing image fusion methods are inseparable from classical mathematical models, and the calculations are complex. Some methods require a large number of iterations, and some involve basic tools to solve problems, etc.

Images