Multi-Sequence Image Fusion Method Based on Adaptive Blocking
An image fusion and sequence image technology, applied in the field of image fusion, can solve problems such as the inability to clarify the regional characteristics of image blocks, the inability to accurately describe the clear focus characteristics of image blocks, and "block effects" to achieve high judgment efficiency, fast fusion speed, and effective results. Good results
Active Publication Date: 2022-04-01
NANJING UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] There are many multi-sequence image fusion methods, such as: weighted average method, wavelet transform image fusion method, image block fusion method, etc. The existing image block problems mainly lie in: 1. On the selection of image block size, the There are too many or too few blocks, which makes it impossible to clarify the regional characteristics of the image block, which will cause serious "block effect"; 2. The clear focus characteristics of each image block cannot be accurately described
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0062] In this embodiment, 50 sequential images of water cotton cells at different focus positions were taken through a microscope system 20× (NA=0.5), and image fusion processing was performed on the collected images based on Visual Studio software. The specific implementation process of the inventive method is as follows: figure 1 shown, including the following steps:
[0063] Step 1. Adopt 20×(NA=0.5) microscope system to take 50 images of water cotton cells and transmit them to the computer processing system. The focus position of the images differs by 1.25 μm, and the pixel size of each image collected is 1280 ×960; perform denoising, enhancement and other preprocessing on the sequence image; obtain the definition value of each pattern in the sequence image through the definition evaluation operator based on wavelet transform on the sequence image, and take the image with the largest definition value as the sample Figure L Temp ; Among them, the calculation method of th...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention proposes that the present invention discloses a multi-sequence image fusion method based on self-adaptive partitioning, which judges the sharpness of pre-segmented image blocks based on wavelet transform. If it is greater than the user-defined threshold, write the image block with a large resolution value into the fusion result image. If not, perform adaptive fine-segmentation on the two comparison images until the specified minimum pixel block is segmented, and write the image block with a large resolution value into the fusion result image. The image blocks of are written into the fusion result map. The invention can realize good image fusion effect, greatly improves the accuracy of block definition judgment, and improves the fusion effect.
Description
technical field [0001] The invention relates to image fusion technology, in particular to a multi-sequence image fusion method based on adaptive block. Background technique [0002] In order to comprehensively describe images of different depths, objects with different focal lengths can be photographed, multiple obtained images with different focal lengths can be merged into one image, and clear parts of different images can be retained. This technology becomes a multi-sequence image Fusion technology, which has the characteristics of large amount of image information and rich details. [0003] There are many multi-sequence image fusion methods, such as: weighted average method, wavelet transform image fusion method, image block fusion method, etc. The existing image block problems mainly lie in: 1. On the selection of image block size, the There are too many or too few blocks, which makes it impossible to clarify the regional characteristics of the image block, which will ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/50
CPCG06T5/50
Inventor 陈文建张璐李武森
Owner NANJING UNIV OF SCI & TECH