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

Method for extracting incomplete data symmetry characteristics based on extended Gaussian ball and M estimation

An extraction method, an incomplete technology, applied in the field of computer vision, can solve the problem that the Gaussian image is not unique

Inactive Publication Date: 2016-12-07
YANGZHOU UNIV
View PDF1 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is a flaw in the extended Gaussian image. For the concave 3D model, the Gaussian image is not unique.

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 extracting incomplete data symmetry characteristics based on extended Gaussian ball and M estimation
  • Method for extracting incomplete data symmetry characteristics based on extended Gaussian ball and M estimation
  • Method for extracting incomplete data symmetry characteristics based on extended Gaussian ball and M estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The specific implementation of the present invention will be further described below in conjunction with the accompanying drawings and the method for extracting symmetric features of incomplete data based on the fusion of extended Gaussian sphere and M estimation.

[0056] 1) Scan the defective face model

[0057] At present, for collecting three-dimensional facial data, a method based on a three-dimensional scanner can be used to obtain more accurate facial shape and texture information.

[0058] 2) Establish an extended Gaussian diagram and find the corresponding points

[0059] (1) if figure 2 As shown, the establishment method of the extended Gaussian map is as follows: In order to remove the noise point cloud in the point cloud data and establish the spatial topology relationship, it is necessary to process the scanned point cloud data:

[0060] a. Firstly, the topology structure based on spatial rasterization is used to establish the spatial topology relationsh...

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 relates to a method for extracting incomplete data symmetry characteristics based on an extended Gaussian ball and M estimation, belonging to the field of computer vision. The method disclosed by the invention comprises the following steps of: (1), scanning a defect facial model by adopting a method based on a three-dimensional scanner so as to obtain initial mirror image data; (2), establishing a spatial topological relationship between a point and a point by adopting a topological structure based on spatial rasterization so as to eliminate noise point cloud, performing K neighbourhood searching, and then, establishing the extended Gaussian ball through normal information so as to find out a corresponding point; (3), roughly aligning the corresponding point based on a principle axis; (4), finely aligning in combination with an M estimation ICP algorithm; and (5), performing least square fitting of a point set in the corresponding point to calculate a central symmetry surface. According to the method disclosed by the invention, the extended Gaussian ball and advantages of an improved ICP algorithm are combined; therefore, characteristic extraction can be carried out more precisely; and more characteristic extraction complex conditions can be satisfied.

Description

technical field [0001] The invention relates to a method for extracting symmetric features of incomplete data, in particular to a method for extracting features of incomplete data based on fusion of extended Gaussian sphere and M estimation, belonging to the field of computer vision. Background technique [0002] Due to the popularity of computer graphics scanning equipment and geometric modeling software, as well as the improvement of the cost performance of graphics processing hardware, more and more 3D models have been widely used in various fields, so the feature extraction method of 3D models has become the key. For the extraction of the model, the first step is to preprocess the coordinates of the model, and principal component analysis (PCA) is often used. The traditional PCA algorithm will have such problems in the retrieval of 3D models. If PCA is used to preprocess the model described by triangular patches, the PCA frame obtained after processing will be different ...

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 Applications(China)
IPC IPC(8): G06T7/00
CPCG06T2207/10028
Inventor 孙进丁静刘远黄则栋杨晗马煜中
Owner YANGZHOU 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