Supercharge Your Innovation With Domain-Expert AI Agents!

Video Face Detection Evaluation Method

A technology of face detection and evaluation method, which is applied in the field of video face detection and evaluation, which can solve the problems of repeated collection and poor effect, unfavorable recognition and use viewing, saving snapshots to increase transmission and storage, etc., to achieve the effect of improving the use value

Active Publication Date: 2018-08-03
SHENZHEN INFINOVA
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, traditional face detection usually detects in real time, so a large number of repeated snapshots of different faces of the same object will be generated during the detection process, which may cause several identical face snapshots to be detected in the screen within the contact time period T. For the face of the object, all the snapshots are saved to increase the transmission storage, which is not conducive to recognition and use and viewing. Therefore, it is necessary to solve the problem of repetition and poor effect of such real-time face detection collection

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
  • Video Face Detection Evaluation Method
  • Video Face Detection Evaluation Method
  • Video Face Detection Evaluation Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] The skin color detection binary mask image of the image frame is obtained by traversing and judging whether the color of each pixel in the image frame in the YCbCr color space satisfies both Cb∈[80,135] and Cr∈[136,177].

[0086] This embodiment is actually a judgment on the color of the pixel in the YCbCr color space, and Cb∈[80,135] and Cr∈[136,177] are determined to be optimal after combining a large number of experiments, and are in line with the YCbCr color space of human skin color. Cb, Cr chroma.

Embodiment 2

[0088] In the above-mentioned frontal face possibility assessment, the face area proportion sequence in step S612 is calculated by dividing the accumulated value in the area corresponding to the face position information on the skin color detection binary mask image by the area length and width.

[0089] Let the face area proportion sequence be {complexionlist t}(0

[0090]

[0091] In the formula, MASK1 is the binary mask image for skin color detection, sx t ,ex t ,sy t ,ey t It is the coordinate values ​​of the four vertices of the rectangular window of the area of ​​face position information at time t, rectwidth t Rectheight is the width of the rectangular window of the area of ​​face position information at time t t is the height of the rectangular window of the area of ​​face position information at time t.

Embodiment 3

[0093] In the above sharpness evaluation, the sharpness value sequence in step S626 is calculated by dividing the cumulative value in the region corresponding to the face position information on the difference binary mask image by the length and width of the region.

[0094] Let the sequence of sharpness values ​​be {definition t}(0

[0095]

[0096] In the formula, SMASK1 is the difference binary mask image, sx t ,ex t ,sy t ,ey t It is the coordinate values ​​of the four vertices of the rectangular window of the area of ​​face position information at time t, rectwidth t Rectheight is the width of the rectangular window of the area of ​​face position information at time t t is the height of the rectangular window of the area of ​​face position information at time 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 present invention provides a video human face detection and evaluation method. After selecting the evaluation object of the input video, the optimal human face evaluation is carried out by considering the size, definition and possibility of the frontal face of the human face, and then the optimal human face is selected. . The beneficial effects of the present invention are: after selecting the evaluation object for all the pictures of the continuous video, further comprehensively judge the size, clarity, and frontal possibility of the human face of the evaluation object, so that the same human face can be evaluated on the basis of tracking the human face. Evaluate snapshots at different moments of the face and output the snapshot at the best moment of the face as an output snapshot for use and retention. It solves the problem that the previous video face recognition will generate a large number of repeated face snapshots, which will lead to a large storage and calculation workload of the back-end server. At the same time, it solves the problem of repetition and poor effect of real-time face detection and collection, and effectively improves the use value of face snapshots.

Description

technical field [0001] The invention relates to a video image processing method, in particular to a video face detection and evaluation method. Background technique [0002] In the real-time video surveillance system, there are real-time detection and collection of face images from different angles, and then uploaded to the server database to store key information and then perform application requirements for criminal suspect face recognition. [0003] However, traditional face detection usually detects in real time, so a large number of repeated snapshots of different faces of the same object will be generated during the detection process, which may cause several identical face snapshots to be detected in the screen within the contact time period T. For the face of the object, all snapshots are saved to increase the transmission and storage, which is not conducive to recognition and use viewing. Therefore, it is necessary to solve the problem of repetition and poor effect o...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/16G06V10/757
Inventor 李杨莫平华刘军
Owner SHENZHEN INFINOVA
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com