Video face detection and evaluation method

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

Active Publication Date: 2015-11-11
SHENZHEN INFINOVA
View PDF6 Cites 23 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 conta

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 and evaluation method
  • Video face detection and evaluation method
  • Video face detection and 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] complexionlist t = ( Σ i > sx t i ≤ ex t Σ j > sy 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 face detection and evaluation method. After selection of an evaluation object is performed on an input video, optimal face evaluation with combination of size, definition and front face possibility is performed on a face, and then an optimal face is selected. The method has the beneficial effects that: after the evaluation object is selected from all images of continuous videos, a comprehensive judgment of the size, definition and front face possibility is further performed on the face of the evaluation object, so that snapshots of the same face at different moments are evaluated based on face tracking to output the snapshot of the human face at the optimal moment as an output snapshot for use and reservation. According to the method, the problem of large storage and computing amounts of a back-end server caused by a large amount of repeated face snapshots generated in conventional face identification is solved, and the problems of duplication and poor effects in acquisition for real-time face detection are solved, and the useful value of the face snapshot is effectively improved.

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/16G06V10/757
Inventor 李杨莫平华刘军
Owner SHENZHEN INFINOVA
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