3D dynamic portrait recognition monitoring device and method

A technology for portrait recognition and monitoring equipment, applied in the field of face recognition, can solve the problems of reducing the accuracy of 3D portrait recognition, reducing the efficiency of recognition, and complex recognition methods, so as to improve the clarity, improve the accuracy, and reduce the occupation. effect of space

Pending Publication Date: 2020-12-08
广州市标准化研究院
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing 3D portrait recognition technology does not preprocess the image during operation, which reduces the accuracy of 3D portrait recognition.
At the same time, the existing 3D portrait recognition technology reduces the efficiency of recognition due to the complexity of the recognition method.
[0003] Through the above analysis, the problems and defects of the existing technology are as follows: However, the existing 3D portrait recognition technology does not preprocess the image during operation, which reduces the accuracy of 3D portrait recognition
At the same time, the existing 3D portrait recognition technology reduces the efficiency of recognition due to the complexity of the recognition method.

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 dynamic portrait recognition monitoring device and method
  • 3D dynamic portrait recognition monitoring device and method
  • 3D dynamic portrait recognition monitoring device and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0098] The 3D dynamic portrait recognition monitoring method provided by the embodiment of the present invention is as follows: figure 1 As shown, as a preferred embodiment, such as image 3 As shown, the method for extracting human face feature points according to the processed human face image through the feature point extraction program provided by the embodiment of the present invention includes:

[0099] S201. After the preprocessing of the human face image is completed, a face feature point extraction model based on a deep convolutional neural network DCNN is established based on the processed human face image by using the feature point extraction program through the face feature point picking module.

[0100] S202. Train the face feature point extraction model, the training samples are two face pictures and corresponding N areas in the images, and the samples in each area correspond to each area convolutional neural network.

[0101] S203, using the face feature point ...

Embodiment 2

[0104] The 3D dynamic portrait recognition monitoring method provided by the embodiment of the present invention is as follows: figure 1 As shown, as a preferred embodiment, such as Figure 4 As shown, the method for converting a two-dimensional face image into 3D human face image data by a 3D face modeling module provided by the embodiment of the present invention includes:

[0105] S301. The face feature point picking module acquires image feature points, and establishes a corresponding image feature set.

[0106] S302. According to the image feature set, the information of the brightness change is clarified, and processed into a primitive map.

[0107] S303. Transform the depth space coordinates into a 3D human face image according to the established primitive map.

[0108] The information for brightness change provided by the embodiment of the present invention also includes: corners, edges, textures, lines, boundaries, and depth and contours in scenes where human faces ...

Embodiment 3

[0116] The 3D dynamic portrait recognition monitoring method provided by the embodiment of the present invention is as follows: figure 1 As shown, as a preferred embodiment, such as Figure 5 As shown, the method for classifying the acquired human face images through the image classification program provided by the embodiment of the present invention includes:

[0117] S401. Establish a corresponding training set and a test set with the acquired human face images.

[0118] S402. Input the image data of the training set into the established data classification model, continuously train and evaluate the classification model, and enable the classification model to correct errors and learn experience.

[0119] S403, after the classification model training is completed, input the test set into the classification model to classify the human face image.

[0120] The method for training and evaluating the classification model provided by the embodiment of the present invention is as...

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 belongs to the technical field of face recognition, and discloses a 3D dynamic portrait recognition monitoring device and method. The system comprises an image acquisition module, an image processing module, a human face feature point pickup module, a 3D human face modeling module, a central processing module, a wireless signal transmission module, a monitoring terminal, a database,a human face recognition and judgment module, a human face search module, a human face image storage module, an image classification module and a display module. According to the invention, the camerais used to obtain the human face image data, and the image is preprocessed, so that the definition of the image is improved, the 3D image recognition of the human face image in subsequent steps is facilitated, and the accuracy is improved; according to the method, the feature points of the human face are extracted through the feature point extraction program, the two-dimensional face image is converted into the 3D human face through the 3D face modeling technology, and the problem that the traditional two-dimensional image recognition precision is low is avoided.

Description

technical field [0001] The invention belongs to the technical field of face recognition, and in particular relates to a 3D dynamic portrait recognition monitoring device and method. Background technique [0002] At present, with the application of deep learning methods, the recognition rate of dynamic portrait recognition technology has been qualitatively improved. At present, the dynamic portrait recognition rate of our company has reached 99%. Compared with other biometric identification technologies, dynamic portrait recognition technology has natural and unique advantages in practical applications: it can be directly acquired by the camera, and the identification process can be completed in a non-contact manner, which is convenient and fast. The current dynamic portrait recognition technology has been applied in finance, education, scenic spots, tourism, social security and other fields. Dynamic portrait recognition technology is mainly divided into two parts: the first...

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): G06K9/00G06K9/34G06K9/62G06T5/00G06T17/00
CPCG06T5/002G06T17/00G06V40/168G06V40/172G06V20/52G06V10/267G06F18/253G06F18/214
Inventor 杨晓峰张颖
Owner 广州市标准化研究院
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