Abstract
In the design of dental multifunctional Cone Beam Computed Tomography, the linear scanning strategy not only saves equipment cost, but also avoids the demand for patients to be repositioned when acquiring lateral cranial sequence images. In order to obtain panoramic images, we propose a local normalized cross-correlation stitching algorithm based on Gaussian Mixture Model. Firstly, the Block-Matching and 3D filtering algorithm is used to remove quantum and impulse noises according to the characteristics of X-ray images; Then, the segmentation of the irrelevant region and the extraction of the region of interest are performed by Gaussian Mixture Model; The locally normalized cross-relation is used to complete the registration with the multi-resolution strategy based on wavelet transform and Particle Swarm Optimization algorithm; Finally, image fusion is achieved by the weighted smoothing fusion algorithm. The experimental results show that the panoramic image obtained by this method has significant performance in both subjective vision and objective quality evaluation and can be applied to preoperative diagnosis of clinical dental deformity and postoperative effect evaluation.
Highlights
Oral disease is common and frequently occurring in all ages
M song et al [14] combined the method based on Scale Invariant Feature Transform (SIFT) feature and mutual information to achieve remote sensing image registration from Coarse-to-fine
The results show that the measurement function proposed in this paper has higher accuracy for the same sequence image registration
Summary
Oral disease is common and frequently occurring in all ages. With the improvement of medical the level, oral imaging has been widely used in preoperative diagnosis and postoperative evaluation of orthodontics, dental implant [1]. M song et al [14] combined the method based on SIFT feature and mutual information to achieve remote sensing image registration from Coarse-to-fine. Sensors 2021, 21, 2200 cranial sequence images, it is difficult to extract enough feature points from the images to be stitched, and the stability of continuous stitching cannot be guaranteed In view of these difficulties, a local normalized cross-correlation stitching algorithm based on Gaussian Mixture Model (GMM) is suggested. In order to eliminate the influence of the irrelevant regions in X-ray image stitching, a local normalized cross-correlation registration based on GMM is proposed.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
