Feature point location method in cephalometric image based on 3D random forest model

A technology of random forest model and feature point positioning, applied in image analysis, calculation model, biological model, etc., can solve the problems of unreasonable spatial distribution and spatial inconsistency of anatomical marker points, and achieve the purpose of strengthening spatial consistency, improving quality, Accurately Detected Effects

Active Publication Date: 2019-08-02
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies in the prior art, and propose a method for locating feature points in cephalometric images based on a three-dimensional random forest model, which solves the anatomical markers detected due to spatial inconsistency in the existing methods The problem of unreasonable point space distribution

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
  • Feature point location method in cephalometric image based on 3D random forest model
  • Feature point location method in cephalometric image based on 3D random forest model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0028] A method for locating feature points in a cephalometric image based on a three-dimensional random forest model of the present invention, see figure 1 shown, including the following process:

[0029] In step (1), a certain number of three-dimensional cephalometric CBCT images are obtained as a training image set.

[0030] The training image size is 512x512x60 pixels.

[0031] In step (2), several sampling points are randomly selected in each training image, and the 3D Haar-like features of each sampling point are calculated and used as 3D appearance features.

[0032] The number of sampling points randomly selected in each training image is 200. The definition of the three-dimensional ...

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 method for locating feature points in a cephalometric image based on a three-dimensional random forest model, and belongs to the technical field of image processing. The method includes: constructing a double-layer regression forest model for each target feature point, and using each training image to train the double-layer regression forest model for each target feature point to obtain the predicted displacement field corresponding to each feature point; The photogrammetric image is used to predict the double-layer regression forest model corresponding to each feature point that has been trained, and the displacement field of each feature point is obtained; the corresponding offset distance map is calculated according to the displacement field of each feature point. Graph calculation to obtain the coordinate position of each feature point. In the present invention, each target feature point has a double-layer regression forest model as a feature point detector, and the second-layer regression forest can significantly improve the quality of each predicted displacement field, so this method can detect more accurately than the traditional method. Anatomical feature points.

Description

technical field [0001] The invention relates to the technical field of image feature point positioning, in particular to a method for locating feature points in a cephalometric image based on a three-dimensional random forest model. Background technique [0002] Three-dimensional CBCT (cone beam CT) cephalometric analysis is an important method in orthodontic treatment, which mainly studies the morphological structure of the human head and face. Through the measurement and calculation of the angle, distance or ratio between the relevant soft and hard tissue feature points in the three-dimensional CBCT cephalometric image, it can clearly understand the structure of the dental jaw and craniofacial soft and hard tissue and their relationship to further Understand its internal structure, reveal the mechanism of cranial, collar, and facial deformities, and provide accurate quantitative information for disease diagnosis, treatment planning, evaluation of treatment results, and gro...

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): G06T7/73G06N3/00
Inventor 戴修斌王洪花刘天亮晏善成
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap