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

Method for describing three-dimensional auricle shape features based on local salience and two-dimensional main manifold

A technology of shape features and three-dimensional scanning, which is applied in image data processing, instruments, calculations, etc.

Inactive Publication Date: 2014-08-13
LIAONING NORMAL UNIVERSITY
View PDF1 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, so far there is no report on the description of 3D auricle shape characteristics based on local saliency and 2D main shape

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
  • Method for describing three-dimensional auricle shape features based on local salience and two-dimensional main manifold
  • Method for describing three-dimensional auricle shape features based on local salience and two-dimensional main manifold
  • Method for describing three-dimensional auricle shape features based on local salience and two-dimensional main manifold

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Proceed as follows:

[0033] a. For the 3D scanning point cloud of the auricle, based on the Gaussian weighted average of the average curvature, calculate the salient eigenvalues ​​on the auricle point cloud, and arrange all the salient eigenvalues ​​in descending order;

[0034] For the 3D scanning point cloud collection of the pinna V= { v i | v i =( x i , y i , z i ), i= 1, 2, …, n}, based on the second basic form of the surface, the principal curvature of each point is discretely estimated, and the auricle point cloud collection is recorded V any point on The two principal curvatures of k1i and k 2i , and remember v i The average curvature of φ ( v i )=( k 1i + k 2i ) / 2; in points v i as the center of the sphere, with 2 σ For radius, establish points based on kd-tree parallel fast search v i Neighborhood point set of N ( v i , 2 σ ), then the neighborhood N ( v i , 2 σ ) The average curvature Gaussian weighted mean of each...

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 describing three-dimensional auricle shape features based on local salience and two-dimensional main manifold. The method is high in shape feature approximation accuracy, and can effectively improve registering efficiency and precision. The method comprises the steps that salience feature values on an auricle point cloud are calculated based on the Gaussian weighted average of average curvature for the three-dimensional point cloud of the auricle, and descending ordering is carried out on all the salience feature values; the salience key points of the three-dimensional auricle point cloud are optimized and selected based on the rejection strategy of Poisson sampling; principal component analysis is carried out on shape information in neighbourhoods of the salience key points of the three-dimensional auricle point cloud based on a two-dimensional main manifold method, and two-dimensional main manifold curved surfaces are formed in a fitting mode; each two-dimensional main manifold curved surface is marked as a high-dimension feature vector, and the high-dimension feature vectors are compressed based on a linear descending dimension method to obtain low-dimension feature vectors of the salience key points of the three-dimensional auricle point cloud.

Description

technical field [0001] The invention relates to a three-dimensional auricle shape feature description technology, especially a three-dimensional auricle shape feature based on local saliency and two-dimensional main shape, which has high shape feature approximation accuracy and can effectively improve registration efficiency and accuracy. Describe the method. Background technique [0002] As a newcomer in the field of biometric identification, the auricle has received more and more attention. The auricle has rich characteristic structures, and its protruding helix, tragus, and between the earlobes, as well as the depressed auricular fossa, scaphoid, and ear cavity, all bring troubles to the description of the local characteristics of the auricle. [0003] Islam et al. used the single-valued surface fitting method on the product-type parameter domain to analyze the 3D scanning point cloud of the auricle. kv i Area N ( kv i , 2 σ ) are fitted (that is, the projection o...

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): G06T7/00
Inventor 孙晓鹏王冠
Owner LIAONING NORMAL UNIVERSITY
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