Supercharge Your Innovation With Domain-Expert AI Agents!

Face key point detection method based on neural network and shape constraint

A face key point and neural network technology, which is applied in the field of face key point detection based on neural network and shape constraints, can solve the problems of large model size, practical application difficulties, and the failure of lightweight models to meet the detection accuracy requirements. , to achieve the effect of improving the detection accuracy and improving the detection accuracy

Active Publication Date: 2021-05-11
ZHEJIANG UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] There is a great correlation between the model size and detection accuracy of traditional deep learning methods. Existing high-precision facial key point detection methods often have large model sizes, and lightweight models often fail to meet the detection accuracy requirements. Difficulties for practical application

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 key point detection method based on neural network and shape constraint
  • Face key point detection method based on neural network and shape constraint
  • Face key point detection method based on neural network and shape constraint

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The method of the present invention will be further described below in conjunction with the accompanying drawings.

[0042] A face key point detection method based on neural network and shape constraints, taking hourglass network and dataset 300W as an example, the specific implementation steps are as follows:

[0043]1. Obtain face data and perform preprocessing, including steps (1) to (2):

[0044] Step (1). Input data set W={(I 1 ,P 1 ),(I 2 ,P 2 ),...,(I n ,P n )}, P={(x 1 ,y 1 ),(x 2 ,y 2 ),...,(x 68 ,y 68 )} where I is the face image, P is the key point coordinate set of the face image, and each face image is marked with 68 key points, (x m ,y m ) is the coordinates of the m key point, n represents the number of face images, I n is the nth face image.

[0045] Step (2). Data preprocessing, unify the face image size to 256*256, and normalize the corresponding key point coordinates at the same time, the normalization formula is

[0046]

[0047] A...

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 key point detection method based on a neural network and shape constraint, and belongs to the field of face recognition and analysis. The method is used for solving the problem of face key point detection, and is mainly applied to face related problems such as automatic face recognition, expression analysis, three-dimensional face reconstruction and three-dimensional animation. The method mainly comprises the following steps: firstly, constructing a shape dictionary according to face key points marked by a training set; then, utilizing a neural network to predict a heat map of a key point in a forward direction; then, according to the heat map, constructing an initial shape feature and a weight matrix; and finally, reconstructing the shape features. The face key point detection under the shielding condition can be realized, the calculation speed is high, the calculation complexity is low, and the detection precision is high.

Description

technical field [0001] The invention belongs to the field of face recognition and analysis and is used for face key point detection, in particular to a face key point detection method based on neural network and shape constraints. Background technique [0002] Face key point detection is a key step in the field of face recognition and analysis. It is the premise and breakthrough of other face-related problems such as automatic face recognition, expression analysis, 3D face reconstruction and 3D animation. In recent years, deep learning methods have been successfully applied to many fields such as image recognition and analysis, speech recognition, and natural language processing due to their automatic learning and continuous learning capabilities, and have brought significant improvements in these areas. Deep learning methods have also made great progress in the research of face key point detection. [0003] There is a great correlation between the model size and detection ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/171G06N3/048G06N3/045G06F18/28G06F18/214
Inventor 丁勇戴悦刘郑学陆晨燕汤峻
Owner ZHEJIANG UNIV
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