Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for achieving face key point detection based on cascade MobileNet-V2

A face key point, cascading technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve the problems of low positioning accuracy and long positioning time, and achieve high accuracy, improved accuracy, and fast speed. Effect

Inactive Publication Date: 2019-06-21
以萨技术股份有限公司 +1
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that there are many methods for face recognition in the prior art, but few of them can be actually used, because most face recognition methods have the disadvantages of low positioning accuracy and long time-consuming positioning, etc. And proposed a method based on cascaded MobileNet-V2 to realize face key point detection

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
  • A method for achieving face key point detection based on cascade MobileNet-V2
  • A method for achieving face key point detection based on cascade MobileNet-V2
  • A method for achieving face key point detection based on cascade MobileNet-V2

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] refer to figure 1 , a method of face key point detection based on cascaded MobileNet-V2, comprising the following steps:

[0026] S1, acquired image data set: collect images with human faces;

[0027] S2, establish MobileNet-V2 cascade network: modify the network input layer in MobileNet-V2, and the convolution layer of MobileNet-V2 is depth-wise convolution for face feature extraction;

[0028] S3, initially determine the key points of the face: use the first neural network in MobileNet-V2 to locate the key points of the face in the picture;

[0029] S4, cutting out the face area: according to the key points of the face determined in S3, the image is cut out, and the area not containing the face in the image is filtered out;

[0030] S5, determine the face area again: use the second neural network in MobileNet-V2 to locate the key points of the face, in which the two neural networks in S3 and S5 adopt a cascaded method to achieve rough to fine Face key point positio...

Embodiment 2

[0034] refer to Figure 1-2 , a method of face key point detection based on cascaded MobileNet-V2, comprising the following steps:

[0035] S1, acquired image data set: collect images with human faces;

[0036] S2, establish MobileNet-V2 cascade network: modify the network input layer in MobileNet-V2, and the convolution layer of MobileNet-V2 is depth-wise convolution for face feature extraction;

[0037] S3, initially determine the key points of the face: use the first neural network in MobileNet-V2 to locate the key points of the face in the picture;

[0038] S4, cutting out the face area: according to the key points of the face determined in S3, the image is cut out, and the area not containing the face in the image is filtered out;

[0039] S5, determine the face area again: use the second neural network in MobileNet-V2 to locate the key points of the face, in which the two neural networks in S3 and S5 adopt a cascaded method to achieve rough to fine Face key point posi...

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 method for achieving face key point detection based on cascade MobileNet-V2 , which comprises the following steps: S1, obtaining a picture data set; S2, establishing a MobileNetV2 cascading network; S3, preliminarily determining the face key point, S4, cutting a face area, S5, determining the face area again, and S6, obtaining an accurate face key point. The invention adopts the MobileNet-V2 neural network with high speed and high precision, and improves it, and uses the two-stage neural network cascading method to improve the accuracy of face detection.; compared with an existing face key point detection model, the method has the advantages of being higher in speed and precision; Through a cascade mode, positioning of fine promotion and refinement is achieved, and cascade network training comprises the steps of firstly training a first-stage cascade network, achieving rough positioning of face key points, then cutting a face area, and then achieving accuratepositioning of the face key points through a second-stage cascade network.

Description

technical field [0001] The invention relates to the technical field of deep learning and artificial intelligence, in particular to a method for detecting key points of a human face based on cascaded MobileNet-V2. Background technique [0002] Face key point positioning is one of the important directions of artificial intelligence research. Face key point detection is also called face key point detection, positioning or face alignment. It refers to locating the key areas of the face given a face image Location, including eyebrows, eyes, nose, mouth, and facial contours, has many applications in real life, such as face recognition, liveness detection, face payment, etc. [0003] There are many methods for face recognition at present, but few of them can be actually used, because most face recognition methods have problems such as low positioning accuracy and long time-consuming positioning. In view of this, the present invention provides a method based on cascaded MobileNet -...

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): G06K9/00G06N3/04G06N3/08
Inventor 段翔李凡平石柱国
Owner 以萨技术股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com