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

Face living body detection method and device based on convolutional neural network

A convolutional neural network and living body detection technology, applied in the field of face liveness detection based on convolutional neural network, can solve the problems of low detection efficiency, high promotion cost, poor user experience, etc.

Pending Publication Date: 2020-11-10
成都奥快科技有限公司
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are mainly two commonly used live face recognition methods. One is the human-computer interaction method. The user needs to complete specified actions, such as opening the mouth, blinking, shaking the head, etc., and the face recognition system judges the detected object by detecting the above actions. Whether it is a real person, this method requires the user to cooperate to complete the specified action, the user experience is not good, and the detection efficiency is low; the other is to use the depth camera to collect the 3D face information of the detected person, and use methods such as optical flow field to extract features Vectors are used to judge live faces. This method needs to add additional equipment, and the promotion cost is high.

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 living body detection method and device based on convolutional neural network
  • Face living body detection method and device based on convolutional neural network
  • Face living body detection method and device based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] Embodiments of the present invention propose a method for face detection based on convolutional neural networks, such as figure 1 As shown, the following steps are included: S101. Obtaining a human face sample image, the human face sample image includes a living human face image and a non-living human face image, and preprocessing the obtained described human face sample image; S102, constructing A convolutional neural network based on living body detection, the convolutional neural network based on living body detection includes a multi-scale attention fusion module; S103, input the face sample image into the convolutional neural network based on living body detection, and train to obtain Convolutional neural network model based on living body detection; S104. Input the face image to be detected into the convolutional neural network model based on living body detection, and determine whether the output data is greater than a preset threshold, and if so, determine the im...

Embodiment 2

[0058] Embodiments of the present invention simultaneously propose a human face liveness detection device 200 based on a convolutional neural network, such as Figure 7 As shown, it includes: an acquisition module 201, which is used to acquire a human face sample image, and the human face sample image includes a living human face image and a non-living human face image, and preprocesses the obtained described human face sample image; Module 202, is used for constructing the convolutional neural network based on living body detection, and the convolutional neural network based on living body detection includes multi-scale attention fusion module; Training module 203, is used for inputting described face sample image into described based The convolutional neural network of living body detection is trained to obtain the convolutional neural network model based on living body detection; the detection module 204 is used to input the face image to be detected into the convolutional n...

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 human face living body detection method based on a convolutional neural network, and the method comprises the steps: obtaining a human face sample image, constructing the convolutional neural network which comprises a multi-scale attention module and is based on living body detection, inputting the human face sample image into the convolutional neural network based on living body detection; training the network to obtain a convolutional neural network model based on living body detection, and inputting to-be-detected face images into the convolutionalneural network model based on living body detection to perform living body face image detection. The embodiment of the invention also provides a human face living body detection device based on the convolutional neural network. According to the embodiment of the invention, the convolutional neural network based on living body detection is constructed, and the convolutional neural network model based on living body detection is trained and optimized, so that living body face recognition can be quickly and accurately realized, the practicability is high, and the face recognition efficiency andsafety are effectively improved.

Description

technical field [0001] The present invention relates to the technical fields of computer vision and image recognition, in particular, to a method and device for human face liveness detection based on a convolutional neural network. Background technique [0002] With the in-depth research and rapid development of computer vision and pattern recognition technology, biometric recognition technologies such as face recognition, fingerprint recognition, and iris recognition have been applied in different scenarios. Among them, face recognition technology has been widely used in many fields such as finance, security and the Internet because of its advantages of convenience and non-contact. At the same time, in order to attack the face recognition system by disguising live faces using photos, videos, masks, etc., how to effectively identify live faces and ensure the security of face recognition systems has become a common concern of users. [0003] At present, there are mainly two ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/161G06N3/045G06F18/25
Inventor 李薪宇
Owner 成都奥快科技有限公司