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

Mouth occlusion judgment method and device, computer readable storage medium and equipment

A mouth and lips technology, applied in the field of mouth occlusion judgment, can solve the problems of high accuracy, good generalization, and strong robustness, and achieve high accuracy, good generalization, and strong robustness

Pending Publication Date: 2022-03-29
BEIJING TECHSHINO TECH +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the technical problem that the mouth occlusion judging method in the prior art has poor versatility and is easily affected by the mouth opening image, the present invention provides a mouth occlusion judging method, device, computer-readable storage medium and equipment, which solves the problem that the mouth occlusion image does not affect the mouth. Misjudgment of occlusion, and high accuracy, good generalization, strong robustness, fast 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
  • Mouth occlusion judgment method and device, computer readable storage medium and equipment
  • Mouth occlusion judgment method and device, computer readable storage medium and equipment
  • Mouth occlusion judgment method and device, computer readable storage medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] An embodiment of the present invention provides a method for judging mouth occlusion, such as figure 1 As shown, the method includes:

[0078] S100: Acquire a face image and locate key points of the face.

[0079] This step does not limit the method of obtaining the face image. For example, the face image can be collected through the face lens. When collecting, a single image can be collected, or a video can be collected, and a single frame or multiple frames can be obtained from the video. image.

[0080] After obtaining the face image, face detection and key point positioning are required. For example, an SSD face detector can be used for face detection on the face image, and then the TDCNN method can be used for key point positioning to obtain the key points of the face. coordinate. The face detector is not limited to SSD, you can also use CRAFT, ADABOOST, etc. In the same way, the facial key point positioning method is not limited to using TDCNN, and SDM can als...

example 1

[0095] Such as Figure 6 As shown, this example directly uses the distance h between the upper and lower lips as the degree of mouth opening. The larger the distance, the greater the degree of mouth opening. When the distance h is greater than the set threshold, it can be considered that the face image is divided into mouth images. .

example 2

[0097] Because different users have different mouth sizes, and when collecting face images, due to the imaging rules of cameras and other acquisition devices, the size of the face images collected at different distances is different. This will lead to a deviation in directly using h as the degree of mouth opening, so that there is an error when the face image is divided into an image with an open mouth or an image with a non-open mouth.

[0098] In order to solve the above problems, this example uses the ratio h / w of the distance h between the upper and lower lips and the distance w between the left and right eyes as the degree of mouth opening. Since the distance w between the left and right eyes of the same user is not changed in practice, h / w can be accurately describes the degree to which the mouth is open.

[0099] Based on this example, as in figure 2 As shown, the aforementioned S200 includes:

[0100] S210: Calculate the vertical distance between the key points of t...

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 mouth occlusion judgment method and device, a computer readable storage medium and equipment, and belongs to the field of biological recognition. The method comprises the following steps: acquiring a face image and positioning to obtain face key points; calculating the mouth opening degree according to the face key points, and dividing the face image into a mouth opening image or a non-mouth opening image according to the mouth opening degree; for the non-mouth-opening image, obtaining a mouth region image from the non-mouth-opening image according to mouth key points in the face key points; and inputting the mouth region image into a pre-trained convolutional neural network, and judging whether the mouth is shielded or not. According to the method, the problem of misjudgment of mouth occlusion caused by the large mouth image is solved, and the method is high in accuracy, good in generalization, high in robustness and high in speed.

Description

technical field [0001] The present invention relates to the field of biometric identification, in particular to a method, device, computer-readable storage medium and equipment for judging mouth occlusion. Background technique [0002] The rise of deep learning has brought great development to biometric recognition, especially research in the fields of face recognition and image understanding. The biological characteristics can not only distinguish the individual organisms, but also judge the state of the individual organisms. When recognizing a human face, it is first necessary to obtain a clear and complete human face image when the light is sufficient, and then perform data processing on the human face image. In face recognition tasks, incomplete or occluded face images will lead to a decrease in accuracy, especially the occlusion of facial features such as the mouth, which has a greater impact on algorithm performance. In addition, the occlusion of the mouth has a grea...

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): G06V40/16G06K9/62G06V10/774G06V10/764
CPCG06F18/2415G06F18/214
Inventor 周军王洋
Owner BEIJING TECHSHINO TECH
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