Unlock instant, AI-driven research and patent intelligence for your innovation.

Human face and feature point detection method and device, electronic equipment and storage medium

A detection method and feature point technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve the problems of increasing time cost, reducing detection speed, and complicated training steps, so as to improve real-time performance and reduce redundancy Parameter calculation, high-precision effect

Inactive Publication Date: 2020-11-10
河南威虎智能科技有限公司
View PDF0 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the complex training steps, they all cause a large number of parameter calculations, which increase the time cost and greatly reduce the detection speed.

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
  • Human face and feature point detection method and device, electronic equipment and storage medium
  • Human face and feature point detection method and device, electronic equipment and storage medium
  • Human face and feature point detection method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to further explain the technical means and effects of the present invention to achieve the intended purpose of the invention, the following in conjunction with the accompanying drawings and preferred embodiments, a detection method, device, electronic The device and storage medium, their specific implementation, structure, features and functions are described in detail as follows. In the following explanations, "first", "second", "first", and "second" are only used for distinction and convenience of description, and do not represent the degree of emphasis of relevant features or the classification of comprehensive primary and secondary. References to "one embodiment" or "another embodiment" are not necessarily to the same embodiment. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the sam...

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 relates to the technical field of human face and facial feature points, in particular to a human face and feature point detection method and device, electronic equipment and a storage medium. The method comprises the following steps: extracting features of a sample image by utilizing a trunk part of a network model, and then calculating and outputting a detection box set and a facialfeature point thermodynamic diagram set; wherein loss value calculation parts of the network model comprise an anchor frame position regression unit, an anchor frame category classification unit anda facial feature point position regression unit for parallel calculation; wherein an anchor frame mechanism is introduced into the network model, a plurality of anchor frames with different scales andsizes is preset, and classification and position regression need to be carried out on each anchor frame; an optimal detection box is screened from the detection box set; points which are screened outfrom the facial feature point thermodynamic diagram set and are greater than a threshold value are used as feature points; and facial feature points corresponding to the optimal detection box are calculated through the coordinates. On the premise of ensuring high precision, redundant parameter calculation is reduced, and the real-time performance is improved.

Description

technical field [0001] The present invention relates to the technical field of human faces and facial feature points, in particular to a detection method, device, electronic equipment and storage medium for human faces and their feature points. Background technique [0002] By analyzing facial features, researchers can obtain a wealth of information, such as identity information, emotional changes, and subjective intentions, etc., and use this information to realize applications such as face recognition, expression recognition, and age recognition, and promote the realization of intelligent society. pace. [0003] Face detection technology is the first step in obtaining facial feature information. This technology can automatically and accurately locate the position of the face, and realize non-contact and imperceptible features. However, the multi-pose characteristics of the face will greatly affect the application based on face detection. Therefore, it is necessary to use ...

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): G06K9/00G06K9/32G06N3/04
CPCG06V40/161G06V40/172G06V40/171G06V10/25G06N3/045
Inventor 桑高丽其他发明人请求不公开姓名
Owner 河南威虎智能科技有限公司