Face pose estimation method, device and apparatus

A face pose and pose angle technology, applied in the field of image recognition, can solve problems such as complex steps, limited precision, and decreased accuracy of output results, and achieve the effects of improving accuracy, speeding up calculation efficiency, and avoiding manual labeling

Active Publication Date: 2019-02-19
SHENZHEN UNIV
View PDF9 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The problem is that the final output is the classification result, and when the sample to be estimated is in the classification boundary interval, the accuracy of t...

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
  • Face pose estimation method, device and apparatus
  • Face pose estimation method, device and apparatus
  • Face pose estimation method, device and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0060] Such as figure 1 as shown, figure 1 A flow chart of a specific embodiment of a human face pose estimation method in the present invention is shown, including the following steps:

[0061] S110, read the picture to be estimated;

[0062] The picture can be collected in real time from the camera or read from a locally stored picture, and the picture can be preliminarily processed by mean filtering.

[0063] S130, according to the first model, identify the face feature points of the picture to be estimated;

[0064] In this embodiment, the first model is trained in advance, so that the first model can recognize the special points of the human face.

[0065] The face feature points are different from the key points of ordinary images. The key points of general images are usually at the maximum or mini...

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 face pose estimation method, device and apparatus, and belongs to the technical field of image recognition. The method comprises the following steps: reading a picture to beestimated; according to the first model, identifying face feature points of a picture to be estimated; according to the second model and the human face feature points, identifying the human face waiting attitude angle of the picture to be estimated. The invention can directly generate real-time face posture angle data and continuously output predicted value, which can be widely used in the application field of real-time and continuously judging face posture. The method can generate training and testing data sets of face posture, avoid manual labeling and improve data set accuracy. At the sametime, a new loss function is proposed for the convolution neural network feature point model in the first model. The new loss function is more conducive to computer operation and speeds up the computational efficiency of the model.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a face pose estimation method, device and equipment. Background technique [0002] At present, facial pose estimation plays an important role in fields such as face recognition and human-computer interaction. Changes in face posture will lead to loss of face information and differences, so that the similarity between the profile faces of different people is higher than the similarity between the profile face and the front face of the same person. In practical applications such as customs, airports, exhibition halls and other public places and public security systems for chasing criminals, current face recognition technology is limited. Therefore, face pose estimation is very important for multi-pose face recognition. In addition, face pose estimation is also widely used in smart cities and driver fatigue detection systems. [0003] According to different impl...

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
IPC IPC(8): G06K9/00G06N3/04
CPCG06V40/168G06N3/045
Inventor 田劲东张祖光李晓宇田勇
Owner SHENZHEN 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