A face detection method based on frequency domain analysis of color video signals

A technology of live detection and frequency domain analysis, applied in the field of face recognition, can solve the problems of high user requirements, high cost, long authentication time, etc., to achieve the effect of good user experience, reduced user cost, and simple algorithm

Inactive Publication Date: 2018-12-28
广州云从洪荒智能科技有限公司
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this type of method is that the requirements for users are too high, which makes the user experience not good, and the authentication time is longer
[0006] 3. Using multi-mode fusion discrimination methods: such as using infrared images to analyze faces, depth cameras to obtain 3D information, joint voice recognition and other methods, such methods require additional equipment assistance, and the 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
  • A face detection method based on frequency domain analysis of color video signals
  • A face detection method based on frequency domain analysis of color video signals
  • A face detection method based on frequency domain analysis of color video signals

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, so as to define the protection scope of the present invention more clearly.

[0033] Such as figure 1 Shown: a face detection method based on color video signal frequency domain analysis, using the following steps,

[0034] Step 1: The image stream acquisition device collects the face video, and sends the face video to the processing module. The image stream acquisition device includes a camera with a resolution greater than 300,000 pixels and a frame rate of 30 frames per second, and a camera connected to the camera. PC, in a stable visible light environment, uses the camera to capture or record a section of color video of the face in real time. During the recording period, the subject keeps a distance of half a meter fro...

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

A method for detecting human faces based on frequency domain analysis of color video signal adopts the following steps: (1) collecting human face video by image stream collecting device and sending the human face video to processing module; 2, detecting and recognizing that face in the face video by a processing module; 3, the processing module selecting the upper frontal region of the face imageas the target region; 4, acquiring the RGB color mean value in the target area, and obtaining the mean value sequence x1 (t), x2 (t), x3 (t) and t of the three channels to represent the time; 5, performing independent component analysis on the RGB signal, and obtaining three component of the independent component analysis as s1 (t), s2 (t) and s3 (t). The use method is user-contactless, and the human face living detection can be completed without completing any action, and the user experience is good.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a face living body detection method based on color video signal frequency domain analysis. Background technique [0002] Face recognition technology is currently one of the most widely used biometric identification technologies, which has the advantages of convenience, user-friendliness, and non-contact. With the wide application in all walks of life, the safety of use has become a common concern. In the face recognition system, criminals can easily use photos and masks to fake faces to carry out attacks and fraud. Therefore, face liveness detection technology has gradually attracted the attention of academia and industry, and its purpose is to distinguish real and fake faces. [0003] The current face detection technology mainly has the following types: [0004] 1. Method based on feature learning: Compared with the real face collected by the same device and the fake face, the...

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): G06K9/00G06K9/62
CPCG06V40/165G06V40/45G06F18/2135
Inventor 夏祥红
Owner 广州云从洪荒智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap