Supercharge Your Innovation With Domain-Expert AI Agents!

3D image pickup-based training method and device

A training device and training method technology, applied in the fields of instruments, character and pattern recognition, computer parts, etc., can solve the problems of difficult to obtain model training data samples, low accuracy of face recognition, etc., and achieve optimized accuracy, data samples high quality effects

Inactive Publication Date: 2018-06-01
UNRE SHANGHAI INFORMATION TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to overcome the defects of difficult acquisition of model training data samples and low accuracy of face recognition in the prior art, and provide a method that can make the data samples as large as possible, the data diversification, and the quality of the data samples. Higher, so that the training method and device based on 3D camera can greatly optimize the accuracy of face recognition

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
  • 3D image pickup-based training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] This embodiment provides a training device based on 3D imaging, and the training device is a computer.

[0049] The training device includes an acquisition module, a lighting module, a generation module, a training module, a projection module, a setting module, a covering module, a selection module and a processing module.

[0050] The obtaining module is used to obtain a 3D model of an avatar.

[0051] The lighting module is used to illuminate the 3D model through at least one virtual light source.

[0052] Various lights when taking pictures can be simulated through the lighting module. Thereby enriching the diversity of data samples.

[0053] The generation module is used to generate a 2D picture library according to the 3D model.

[0054] The projection module is used to project the 3D model onto a unit plane in space to obtain the 2D image library.

[0055] Specifically, the projection of the 3D model in this embodiment onto the unit plane is realized by settin...

Embodiment 2

[0078] This embodiment is basically the same as Embodiment 1, the only difference is:

[0079] The training device of this embodiment also includes an adding module and a recognition module.

[0080] The adding module is used to add a 3D occluder on the 3D model;

[0081] The identification module is used to identify the skin and hair regions in the pictures in the 2D picture library;

[0082] The training module is used for training the model by using the pictures in the 2D picture library after identifying the skin and hair regions.

[0083] This embodiment also provides a training method using the training device described above. The training method refines step 100 in Embodiment 1 into: acquiring a 3D model of an avatar; adding a 3D occluder to the 3D model.

[0084] Step 106 is refined as: the recognition module is used to identify the skin and hair regions in the pictures in the 2D picture library; Model training.

[0085] The training method and device of this embod...

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 3D image pickup-based training method and device. The 3D image pickup-based training method includes the following steps that: the 3D model of a head image is acquired; the 3D model is illuminated through at least a virtual light source; a 2D picture library is generated according to the 3D model; and the model training of the head image is performed through usingthe 2D picture library. With the 3D image pickup-based training method and device of the invention adopted, data samples can be as large as possible and can be diversified; and since the quality of the data samples is high, the accuracy of face recognition can be greatly optimized.

Description

technical field [0001] The invention relates to a training method and device based on 3D photography. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. A series of related technologies that use a video camera or camera to collect images or video streams containing human faces, automatically detect and track human faces in the images, and then perform facial recognition on the detected faces, usually also called portrait recognition and facial recognition. [0003] The research on the face recognition system began in the 1960s. After the 1980s, it was improved with the development of computer technology and optical imaging technology, and it really entered the primary application stage in the late 1990s. Technology implementation is the main focus; the key to the success of the face recognition system is whether it has a cutting-edge core algorithm, and the recognition result has a practical...

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): G06K9/00G06K9/62
CPCG06V40/179G06V40/166G06V40/172G06F18/214
Inventor 吴跃华
Owner UNRE SHANGHAI INFORMATION TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com