Multi-focusing image fusion method based on multi-dimensional image analysis and block consistency verification

Abstract

The invention relates to a multi-focusing image fusion method based on multi-dimensional image analysis and block consistency verification. The method includes the steps of conducting multi-dimensional decomposition for a down-sampled multi-focusing source image, calculating the definition of characteristic high frequency sub-band coefficient and conducting bi-side filtering to obtain an initial binary image, conducting up-sampling after processing isolated small areas in areas in the initial binary image, replacing the up-sampled binary image boundaries with original boundaries of a source image, conducting partitioning processing and block consistency verification to finally optimize the binary image boundaries, and conducting fusion for the source image accordingly. Optimal boundaries of focusing areas and non-focusing areas of a source image are obtained based on multi-dimensional image analysis and block consistency verification, so as to guarantee direct and accurate fusion of source image focusing areas. The algorithm is simple. The focusing information of a multi-focusing image can be effectively maintained on the premise of introducing no error information.

Description

technical field [0001] The invention belongs to the technical field of image processing data fusion, and in particular relates to a multi-focus image fusion method based on multi-scale image analysis and block consistency verification. Background technique [0002] Image fusion is the process of synthesizing different images acquired by different sensors or different images acquired by the same sensor at different times to obtain a fused image. The fused image contains useful information of all source images in order to better describe the scene and prepare for subsequent image processing tasks such as image segmentation, object detection, image recognition, etc. Image fusion technology plays an important role in medical imaging, microscope imaging, computer vision and military applications. [0003] Due to the limited field of view of the optical lens, it is difficult to obtain an all-in-focus image that can be used to describe and analyze all objects in a scene. Multi-fo...

AI Technical Summary

Problems solved by technology

The pixel-based method determines the focus of a single pixel, ignoring the correlation between neighboring pixels; one difficulty of the block-based method is the selection of the size of the block. Although the positioning is too large, the positioning may be accurate, but it may also contain fuzzy information. Too small will lead to inaccurate positioning and misjudge the block in the smooth area as a fuzzy block. Even if the adaptive method can optimize the size of the block, due to the difference and complexity of the image content structure information, blocks will inevitably appear. effect; although the method based on region segmentation can achieve certain good results, but this type of method relies too much on the segmentation algorithm, and the complexity of the algorithm is high

Images