Three-dimensional image contour retrieval method and system based on tangential domain and storage medium

A three-dimensional image and contour technology, applied in the field of image processing, can solve problems such as contour deformation, and achieve the effect of strong applicability, simple process and improved retrieval efficiency.

Active Publication Date: 2021-03-23
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The outline of an object is its inherent property, it will not change with the illumination, color and texture, so the target recognition method based on the outline has been studied a lot, but the outline of the object will have different changes in the image as the shooting angle changes. Presentation, the movement and occlusion of non-rigid objects will lead to the deformation of the extracted contours, and the same type of objects will also have different properties. The existence of these problems has brought great challenges to related research. A good trade-off between robustness and

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
  • Three-dimensional image contour retrieval method and system based on tangential domain and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Such as figure 1 Shown, a kind of three-dimensional image contour retrieval method based on tangential field of the present invention, comprises the following steps:

[0036] (1) Projection view generation: Input the 3D image I, zoom and translate it to the center of the unit sphere, use Gauss-Seidel iteration to generate 200 viewpoints on the unit sphere, and generate a projection map at each viewpoint.

[0037] The viewpoints generated by this method are more uniform than the longitude and latitude coordinates, and 200 viewpoints can contain rich detailed information without taking up more calculation time.

[0038] (2) Feature view extraction: the morphological watershed algorithm extracts the sequence contour of each projected image, denoted as C i ,i=1,2...,200, and use the one-dimensional equation C i =x(t)+jy(t) to express, for C i Carry out Fourier series expansion, select the first 20 Fourier coefficients to describe, randomly select 4 cluster centers, clust...

Embodiment 2

[0061] A computer-readable storage medium, on which a computer program is stored, and the computer program implements the above-mentioned tangential domain-based three-dimensional image contour retrieval method.

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 three-dimensional image contour retrieval method and system based on a tangential domain and a storage medium, and the method comprises the steps: carrying out the Kmeans clustering to generate a feature view of a projection view of a three-dimensional image, extracting the contour of the feature view, carrying out convolution by using a Gaussian kernel function and converting the convolution result into a tangential domain for retrieval. The method can eliminate the influence of a starting point on contour retrieval, has rotation, translation, scale and mirror imageinvariance, is low in feature dimension and high in extraction speed, can obtain a higher retrieval rate compared with other contour retrieval algorithms, and has better universality.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a three-dimensional image contour retrieval method, system and storage medium based on a tangential domain. Background technique [0002] The outline of an object is its inherent property, it will not change with the illumination, color and texture, so the target recognition method based on the outline has been studied a lot, but the outline of the object will have different changes in the image as the shooting angle changes. Presentation, the movement and occlusion of non-rigid objects will lead to the deformation of the extracted contours, and the same type of objects will also have different properties. The existence of these problems has brought great challenges to related research. A good trade-off between robustness and robustness. [0003] The current research program for 3D images can directly establish descriptors from the 3D image itself, or indirectly establish descrip...

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): G06F16/583G06T7/13
CPCG06F16/583G06T7/13G06T2207/10012
Inventor 杜娟闫甜甜胡晓明
Owner SOUTH CHINA UNIV OF TECH
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