A Symmetry Analysis Method of 3D Face Model

A face model and analysis method technology, applied in image analysis, image enhancement, instruments, etc., can solve the problems of influence processing, asymmetry of face model, etc., to achieve the effect of improving effectiveness, easy further processing, and increasing the maximum number of

Active Publication Date: 2020-08-18
ZHEJIANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to propose a symmetry analysis method for a three-dimensional face model for the problem that the face model collected by the depth camera Kinect and reconstructed by KinectFusion has a slight asymmetry and affects further processing

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
  • A Symmetry Analysis Method of 3D Face Model
  • A Symmetry Analysis Method of 3D Face Model
  • A Symmetry Analysis Method of 3D Face Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0128] Embodiment 1. The inventors tested the effectiveness of the relaxation factor in the feature-grid matching process proposed by the present invention. figure 2 and image 3 It shows the case of using unity ∈ as the threshold. The left symmetry plane can be clearly seen to be biased to the right (from the observer's perspective) from the nose to the mouth. The matching error of the entire model is relatively large, and the matching of point pairs The hair part is missing again. Figure 4 and Figure 5 It shows the case of using ∈ with a relaxation operation as the threshold, the symmetry plane can bisect the entire face well, the matching error of the whole model is small, and the matching of point pairs is complete, except that some parts of the hair exceed the maximum error threshold Most of the points can be correctly stored except that they are not matched.

Embodiment 2

[0129] Embodiment 2. The inventor tested the effectiveness of the new method in the feature extraction process proposed by the present invention. If using the original n i ×n j To calculate the initial rotation axis, the distribution of Euler angles is obviously too scattered, and since the displacement vector is calculated through Euler angles, its distribution will also be too scattered, which is not conducive to the next clustering. After the improved algorithm, the distribution of Euler angles has three obvious concentration areas. At the same time, the displacement vectors can also be well centered.

Embodiment 3

[0130] Embodiment 3. The inventor tested the effect of the method flow of the present invention on 10 three-dimensional human face models. Experimental results show that the method of the present invention can correctly and efficiently analyze the symmetry of the face model.

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 present invention discloses a symmetry analysis method for a three-dimensional face model. The method comprises: sampling an input face model, and pairing sampling results so as to obtain symmetrical features; and extracting and clustering the obtained symmetrical features, so as to obtain a symmetry relation of the model. According to the method, a PCA constraint is added during feature extraction, which effectively increase the maximum number of initial sampling points when computing resources are limited; by improving the extraction method for the symmetrical feature, the validity of the clustering result is enhanced; and by adding a relaxation factor during feature-grid reassignment, stability of results is ensured and the matching is extended to the whole model. A test is performed on a face model that is acquired at Kinect and reconstructed using KinectFusion, and the validity of the method is verified.

Description

technical field [0001] The invention relates to the field of three-dimensional model processing, in particular to a symmetry analysis method for a three-dimensional human face model. Background technique [0002] Many creatures and objects in nature have certain symmetries. These symmetries include rotational symmetry, mirror symmetry, and fractals. Absolute symmetry is very rare, but when certain prerequisites are met, we can effectively use symmetry to improve the modeling of real-world objects. Among them, the human face is a common research object that satisfies mirror symmetry. In recent years, with the emergence of household depth cameras such as Kinect and research in related fields, people can quickly and efficiently collect and build a large number of face models. However, there is also a slight asymmetry in the face itself, and some errors will be introduced by the acquisition equipment and modeling algorithm. In some studies, however, it is necessary to reduce...

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): G06T7/68
CPCG06T7/68G06T2207/10028G06T2207/30201
Inventor 任重周顺邵天甲周昆
Owner ZHEJIANG UNIV
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