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

Harris-based spine feature point automatic recognizing method

An automatic identification and feature point technology, applied in the field of medical image processing, can solve the problems of low efficiency and high requirements, and achieve the effect of simplifying the operation process and reducing the number of grids

Inactive Publication Date: 2015-09-30
XIDIAN UNIV
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These two methods have high requirements on operators and instruments, and are inefficient

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
  • Harris-based spine feature point automatic recognizing method
  • Harris-based spine feature point automatic recognizing method
  • Harris-based spine feature point automatic recognizing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0086] see figure 1 , figure 1 The process and results of feature point recognition on the human lumbar spine L3 by applying the method of the present invention are shown respectively. The model was verified in the paper (Wang Y, Yu B, Dai J. Three-Dimensional Finite Element Force Analysis and Simulation of Human Spinal Lumbar Segment[J]. Journal of Convergence Information Technology, 2013, 8(4).).

[0087] Step 1, performing three-dimensional reconstruction on the CT image of the human spine to obtain a three-dimensional model of the spine, and cutting the three-dimensional model to obtain the vertebral body for which feature points are to be extracted;

[0088] like figure 2 As shown, after enhancing the CT data and extracting the threshold value, the range of the target vertebral body is segmented, and the following is obtained: image 3 The 3D model shown. The specific construction and segmentation process can be carried out through the ScanIP module of the simplewa...

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 Harris-based spine feature point automatic recognizing method. The Harris-based spine feature point automatic recognizing method comprises the steps of modeling and cutting a spine three-dimensional model through a CT (Computed Tomography) picture; obtaining a specific spine body which is to be subjected to feature point recognition; carrying out meshing on the spine body, and enabling the spine body to be formed by small triangular patches; adaptively calculating a threshold ring number of each one of all vertexes of a spine body model; calculating model vertex normal vectors; obtaining a first feature vector and a second feature vector by analyzing the normal vectors of one vertex and other vertexes within the threshold ring number of the vertex by utilizing a principal component analysis method; carrying out function fitting on the first feature vector and the second feature vector by utilizing a least square method; carrying out vertex variation value calculation on a fitted function by utilizing a Harris algorithm; sorting variation values of all the vertexes in a descending order, and picking out a candidate feature point; carrying out non-maximum suppression on the candidate feature point according to a certain suppression region, and finally obtaining a feature point of the spine body. The Harris-based spine feature point automatic recognizing method disclosed by the invention can be used for research related to spines in the field of surgical sciences.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, and relates to feature point recognition and calibration of vertebral parts, in particular to a Harris-based vertebral feature point automatic recognition method. Background technique [0002] Feature point detection is a hot research field in image processing. A feature point refers to a vertex that is different from other vertex features within a certain range. In 3D objects, feature points can be defined as edges, ridges, valleys, cusps, etc. Feature point recognition refers to the detection and marking of special point sets that meet the definition of feature points on a given object. Applying feature point recognition to medical images can provide reference data for medical diagnosis and avoid errors caused by human factors. At present, feature point recognition technology has been used in medical fields such as skull restoration. [0003] The spine is an important suppo...

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
IPC IPC(8): G06T17/00G06T7/00
Inventor 鱼滨张琛苏仲谋
Owner XIDIAN UNIV
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