Method for image fusion by using multi-scale top-hat selective transform

Abstract

The invention discloses a method for image fusion by using multi-scale top-hat selective transform. The method comprises five major steps of: 1, extracting an effective region in an image by defining parameters in the top-hat selective transform; 2, extracting a multi-scale bright region and a multi-scale dark region of an original image through the defined top-hat selective transform by using multi-scale structural elements; 3, acquiring a bright region and a dark region of a corresponding fused image under each scale by using the maximum value aiming at the bright regions and the dark regions of different original images extracted under each scale; 4, acquiring a bright region and a dark region for final image fusion by taking the maximum value of the bright regions or the dark regions of the corresponding fused image on all scales; and 5, after a basic image is acquired by averaging the original images, adding the acquired bright region to the basic image and subtracting the acquired dark region to fulfill the aim of image fusion respectively, thereby obviously improving contrast of the fused image and image detail. The method is applied to various image based application systems and has broad application prospect.

Description

(1) Technical field [0001] The invention relates to an image fusion method utilizing multi-scale top-hat selective transformation, belongs to the field of digital image processing, and mainly relates to mathematical morphology and image fusion technology. It has broad application prospects in various image-based application systems. (2) Background technology [0002] Image fusion is an important key technology in image processing, and it is an effective tool for rationally and effectively utilizing multiple sensors to obtain data information. The key of image fusion is to extract the useful regions in the original image and merge these regions into the result image reasonably. In order to better extract useful information from images acquired by multiple sensors and fuse them into the same image, various methods have been proposed. The direct averaging method is a simple and effective image fusion method, but this method cannot extract the details of the image very well, a...

AI Technical Summary

Problems solved by technology

Although various image fusion methods are used for image fusion, most methods cannot extract effective image regions in the original image well for image fusion, thus blurring image details or missing part of image information to varying degrees, making image fusion difficult. not effectively

Images