Rapid image fusing method for eliminating splicing slits
An image fusion and gap technology, applied in the field of image processing, can solve the problems of pixel value error, large amount of calculation, etc., and achieve the effect of fast speed and gap elimination
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2017-03-01
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the field of image processing and is used for optimizing spliced images and eliminating gaps in spliced images. Background technique
[0002] In daily life, we can use a wide-angle lens or a scanning camera to capture wide-field images, but such equipment is generally expensive, and the captured images are distorted; The rate is lower. In order to obtain a wide-view image without reducing the image resolution, image stitching technology was created. Image stitching technology uses several small-view images to stitch together a large-view image. We can use image stitching technology Get a panoramic image. This technology is widely used in seabed exploration, remote sensing technology, medical image processing and military fields.
[0003] The core of image stitching technology includes image registration and image fusion. Image registration refers to extracting the matching information in two or more images to be stitche...
Examples
Embodiment Construction
[0025] The traditional algorithm is to perform weighted average operation on all pixels in the overlapping area. If the overlapping area is large, the calculation amount will be very large, but in fact, the weighted average operation on the pixels far away from the stitching gap is unnecessary. In addition, the overlapping area is an irregular image. If the denominators of the weights are the same, errors will occur in the calculation of the pixel value of the pixel.
[0026] To solve the above problems, we propose an improved weighted fusion algorithm for stitched images. figure 1 The thick line in the middle is the gap after stitching the two images. The specific algorithm is as follows:
[0027] Step1: First, we set a threshold T, which is related to the brightness difference of the two images and the size of the overlapping area. The threshold range is generally 16 to 64 pixels.
[0028] Step2: Search for areas in the overlapping area whose distance from the stitching ga...