Face snapshot method and system and storage medium

A face image and face detection technology, applied in the field of computer vision, to achieve the effect of strong interpretability, high system efficiency, and reducing the use of prior knowledge

Pending Publication Date: 2022-01-07
SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical task of the present invention is to provide a face capture method, system and storage medium to solve the problem of how to capture the face with the best quality and the most correct angle in the process of face detection and tracking

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 snapshot method and system and storage medium
  • Face snapshot method and system and storage medium
  • Face snapshot method and system and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] as attached figure 1 As shown, the face capture method of the present invention, the method is specifically as follows:

[0065] S1. Obtain the image data of the current frame of the video;

[0066] S2. Obtain a face image for face detection in the video through the face detection-face key point detection model, and perform face key point detection on the detected face image;

[0067] S3. Obtain several target sequences by matching face coordinates between consecutive frames through a tracking and matching algorithm;

[0068]S4. Calculate the face image quality score according to the face coordinates and key point information;

[0069] S5. Screen out the best face image for each target sequence that meets the requirements according to the face image quality score, and output relevant information corresponding to the best face image.

[0070] In the present embodiment, the face detection-face key point detection model of step S2 adopts MTCNN, Retinaface or OpenFace; ...

Embodiment 2

[0084] as attached figure 2 As shown, the face capture system of the present invention includes,

[0085] The face detection-key point detection module is used to detect the face and key points using the face detection-key point detection network model, and obtain the coordinate information of the face and the key points of the face;

[0086] The tracking and matching module is used to use the tracking and matching algorithm to correlate and match the face sequences of the unified target, and then obtain the relevant information of each target during the tracking process;

[0087] The face quality evaluation module is used to calculate the face image quality score according to the face coordinates and key point information, and then filter out the best face image for each target sequence that meets the requirements according to the face image quality score, and output the best face image. The relevant information corresponding to the face image.

[0088] The working process...

Embodiment 3

[0109] The specific process of the face capture method of the present invention is as follows:

[0110] (1) Acquiring the current frame image data of the video;

[0111] (2), select the pre-trained face detection-face key point detection model (such as MTCNN, Retinaface, OpenFace, etc.), input the result of step (1) into the face detection-face key point detection model, and perform network Forward reasoning, output the face image of the current frame of the video and the information of its key point coordinates, as shown in the attached image 3 shown;

[0112] (3), select a tracking matching algorithm (such as sort, deepsort, KCF, JDE, etc.), input the result of step (2), carry out correlation matching with the results of the front and rear frames of the video, and output information such as the face of the target after the match;

[0113] (4), according to the result of step (3) (face coordinate information etc.), the face image of matching in the image of cropping step (...

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 invention discloses a face snapshot method and system and a storage medium, belongs to the technical field of computer vision, and aims to solve the technical problem of how to snapshot a face with the best quality and the most correct angle in the face detection and tracking process. The adopted technical scheme is as follows: the method specifically comprises the following steps: acquiring current frame image data of a video; detecting a human face in the video through the human face detection-human face key point detection model to obtain a human face image, and performing human face key point detection on the detected human face image; matching the continuous inter-frame face coordinates through a tracking matching algorithm to obtain a plurality of target sequences; calculating a face image quality score according to the face coordinates and the key point information; and according to the face image quality score, screening out an optimal face image meeting the requirement of each target sequence, and outputting related information corresponding to the optimal face image.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a face capture method, system and storage medium. Background technique [0002] Face capture is considered to be a widely used biometric identification technology due to its advantages of non-contact, concealed operation and no need for characteristic cooperation. Face capture technology has been widely used in many fields, such as public security monitoring, traffic checkpoint monitoring, train station face-train ticket recognition and other fields, but the face quality in the process of face capture is low, affected by various factors, Such as face posture, expression, blur, brightness, occlusion, etc. Therefore, in the process of face detection and tracking, how to capture the face with the best quality and the most correct angle is a technical problem that needs to be solved urgently. [0003] Patent No. CN106446851A discloses a face selection method and system base...

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): G06K9/00G06K9/62G06T7/00G06T7/246G06T5/10
CPCG06T7/0002G06T7/248G06T5/10G06T2207/10016G06T2207/20052G06T2207/20081G06T2207/30168G06T2207/30201G06F18/22G06F18/214
Inventor 刘琛耿艳磊李晗安晓博
Owner SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD
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