Multi-focus image fusion method based on decision diagram and sparse representation

Abstract

The invention discloses a multi-focus image fusion method based on a decision diagram and sparse representation. According to the method, a multi-focus image fusion framework which is different from the conventional multi-focus image fusion algorithm is put forward based on the characteristics of a human vision system, and analysis and research are performed for the transition region of multi-focus images so as to avoid the influence on the fusion result and enhance the quality of the fusion image. The implementation process comprises the steps that the decision diagram is generated on the basis of resolution analysis of the low-scale images of the multi-focus images, and a fusion result is acquired according to the decision diagram; the generated decision diagram has error due to the fact that judgment of the resolution of the transition region has deviation so that the transition region requires to be determined and processed by using the multi-focus image fusion algorithm based on sparse representation and the fusion result of the transition region can be acquired; and finally mean operation is performed on the fusion result based on the decision diagram and the fusion result of the transition region so that the final fusion image is acquired.

Description

Technical field [0001] The invention belongs to the field of image processing technology, involving image compression, image sparse representation, image spatial frequency comparison, mathematical morphology technology and image fusion technology, and can be used in the fields of machine vision, target recognition, clear imaging of digital cameras and the like. Background technique [0002] In the shooting process, when the focal length of the imaging system is set, due to the limitation of the lens depth of field, only the images formed by objects within a certain range in front and back of the lens conjugate are clear, and the images formed by objects outside this range are Fuzzy. In actual application, when imaging a certain scene, because the distance between the subject and the lens is different, the resulting image is often not fully clear. In order to obtain a full clear image of the scene, a feasible way is to focus on each object in the scene separately, obtain their cl...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to propose a new multi-focus image fusion framework, that is, a multi-focus image fusion method based on decision graph and sparse representation, which can not only realize the fusion of multiple multi-focus images, but also improve the existing multi-focus image fusion The shortcomings of low applicability of the algorithm, and improving the quality of multi-focus fusion images

Images