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

Face detection model generation and face detection method, device and equipment

A face detection, face area technology, applied in the field of face detection

Pending Publication Date: 2020-09-01
BEIJING HUAJIE IMI TECH CO LTD +1
View PDF12 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the process of practical application, the security problems of face recognition technology have gradually emerged. How to filter out some artificial deceptive means during face recognition has become a hot research direction now.

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 detection model generation and face detection method, device and equipment
  • Face detection model generation and face detection method, device and equipment
  • Face detection model generation and face detection method, device and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0063] Based on the above background technology, it can be seen that for face recognition technology, if you want to apply face recognition technology to mobile phone unlocking, access control, face payment and other usage scenarios with security level requirements, it can be applied to face recognition living body Detection technology is of course essential.

[0064] Existing liveness detection technologies applied to face recognition and their shortcomings mainly include:

[0065] 1. Based on a single color image, the human face in the image is judged in vivo, mainly to check whether the detailed texture is the same as the face image taken by a real person. The main disadvantage of this method is that the data source is single, it is easily affected by factors such as illumination and motion blur, and it has poor resistance to 3D mask and head model attacks, and its robustness is not strong.

[0066] 2. Based on multiple frames of continuous images, the liveness judgment of...

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 embodiment of the invention provides a face detection method, device and equipment. The method comprises the following steps: determining an image group to be subjected to face detection; combining the extracted feature maps of the target images to obtain a first target feature map; performing feature extraction on the first target feature map to obtain a second target feature map, wherein thesecond feature map is composed of vectors of a plurality of preset dimensions; determining each anchor point area associated with the vector in a preset image group, and calculating an information group of each anchor point area according to the vector; determining a candidate face area of the image group according to the information group of each anchor point area associated with each vector inthe second feature map; and generating a face detection result (the face detection result comprises a face region in the image group and a living body detection result of the face region) of the imagegroup based on the feature region matched with the candidate face region in the first feature map, thereby achieving the purpose of realizing living body detection of the face while realizing face detection.

Description

technical field [0001] The present invention relates to the technical field of face detection, and more specifically, to a face detection model generation and face detection method, device and equipment. Background technique [0002] Biometric technology has come a long way since the last century. Technologies such as fingerprint recognition, iris recognition, voiceprint recognition, and face recognition are becoming more and more mature, and are gradually being applied to people's production and life. Among them, face recognition technology has become one of the most popular biometric recognition technologies due to its intuitive and easy-to-acquire data. [0003] For a long time, people have been concerned about the accuracy of face recognition technology, that is, whether it can recognize the same face in different shooting environments, and whether it can distinguish between two similar but different faces. different faces. However, in the process of practical applica...

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): G06K9/00G06K9/46G06K9/62G06N3/04
CPCG06V40/161G06V40/168G06V40/45G06V10/56G06N3/045G06F18/214
Inventor 张玏李骊董晶金博王鹏
Owner BEIJING HUAJIE IMI TECH CO LTD