Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Skeleton Line Extraction Method Based on Projection Matching Group

A projection matching and extraction method technology, applied in the field of computer vision, can solve the problems of poor universality, long time consumption, poor positioning effect, etc. Effect

Active Publication Date: 2021-03-02
UNIV OF ELECTRONICS SCI & TECH OF CHINA +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the technical problems such as poor positioning effect, long time consumption and poor universality of the existing technology, the present invention provides a skeleton line extraction method based on projection matching group

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Skeleton Line Extraction Method Based on Projection Matching Group
  • Skeleton Line Extraction Method Based on Projection Matching Group
  • Skeleton Line Extraction Method Based on Projection Matching Group

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] This example proposes a skeleton line extraction method based on projection matching group, using grid projection technology to map the tooth point cloud to a two-dimensional plane, and then using morphological operations to denoise to obtain tooth structure, and then using coordinate matching group technology to obtain three-dimensional teeth Skeleton lines, such as figure 1 shown.

[0060]The method of this embodiment specifically includes the following steps:

[0061] 1. Tooth point cloud grid projection

[0062] Since a jaw point cloud has tens of thousands of three-dimensional points, for the convenience of description, this embodiment only deduces a local point cloud Q of the whole. The point cloud Q consists of four points, namely:

[0063] A=(x 1 ,y 1 ,z 1 ), B=(x 2 ,y 2 ,z 2 ), C=(x 3 ,y 3 ,z 3 ), D=(x 4 ,y 4 ,z 4 ). In order to obtain the two-dimensional skeleton line, the plane where the two-dimensional skeleton line is located is the O-XY pla...

Embodiment 2

[0114] Based on the 3D skeleton line extraction method based on the projection matching group proposed in the above-mentioned embodiment 1, the method of this embodiment also includes based on the extracted 3D skeleton line, using the spatial position of the overlapping area and the skeleton line, and using the normal distance as a criterion from The overlapping regions are classified in the gingiva point cloud, as follows:

[0115] The main function of the extracted skeleton line is that since the skeleton line is in the center of the tooth point cloud, it can be used as a dividing line to distinguish the buccal gingiva and lingual gingiva by using the positive and negative normal distances, as well as the buccal gingiva line and lingual side gum line, and the buccal gum line is the anterior arch, and the buccal gum is the overlap area.

[0116] The specific process of extracting the anterior dental arch using the skeleton line is as follows:

[0117] Let the extracted skele...

Embodiment 3

[0124]In this embodiment, the skeleton line extraction algorithm based on projection matching group in the above-mentioned embodiment 1 is compared with the existing iterative refinement algorithm based on Laplacian operator; the experimental results given in this embodiment are all based on the Matlab experimental environment, It runs on a PC with CPUIntel(R)Core(TM)i3-6100@3.70GHz and 8G memory, and the operating system is Windows 64-bit operating system. For the same jaw point cloud, under different sampling conditions, the number of different point clouds and the number of triangle meshes (jaw 1: vertices: 19601, faces: 38084; jaw 2: vertices: 13865, faces: 26277; jaw 3: Vertices: 10557x3, faces: 19816x3; Jaw 4: vertices: 5945, faces: 10719; Jaw 5: vertices: 1532, faces: 2698; ) to compare the effect of the algorithm. Analyze the effect of skeleton line extraction and the time-consuming algorithm under different numbers of point clouds and triangular meshes. Take jaw 1 as...

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

No PUM Login to View More

Abstract

The invention discloses a skeleton line extraction method based on a projection matching group. The invention uses grid projection technology to map tooth point clouds to a two-dimensional plane, and then uses morphological operations to denoise to obtain tooth structures, and then uses coordinate matching group technology to obtain three-dimensional Teeth skeleton line: Compared with the traditional method, the skeleton line extraction method proposed by the present invention has significantly improved effect and time-consuming, and greatly improved the accuracy and reliability of overlapping area positioning.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for extracting skeleton lines based on projection matching groups. Background technique [0002] Skeleton - the central axis of the target graphic image, that is, a set of all center point elements (skeleton subsets), which can effectively reflect the connectivity of the shape of the object in the graphic image and the topology of the geometric shape of the graphic image. In computer vision technology play a pivotal role. [0003] In the medical field, skeleton extraction technology is even more important. Extracting the target skeleton from medical images obtained from various medical equipment is one of the most basic tasks in medical image processing. Many scholars at home and abroad have already carried out long-term research and achieved certain results. [0004] With the continuous advancement of technology, 3D lidar has reached sub-millimeter resolution,...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T3/00
CPCG06T3/067
Inventor 李小兵罗嘉庆潘毅
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com