Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method, device and medium for acquiring face recognition model training data based on video

A face recognition and model training technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of uneven quality of star pictures, low efficiency, photos that do not conform to model training, etc., to alleviate repeated recognition problem, the effect of reducing duplicate video frames

Active Publication Date: 2019-01-29
BEIJING YINGPU TECH CO LTD
View PDF8 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Either way, manual participation is required, and there are respective defects: the quality of star pictures obtained in the network gallery is uneven, and many photos do not meet the needs of model training. More importantly, the most original recorder When entering a picture into a search engine, the entrant will set keywords based on some information of the picture. For example, if the description information of a picture to be entered is "Star A and Star B promote the new drama XX", there may be only Celebrity B, without Celebrity A, but the description information of the picture includes keywords: Celebrity A's "name"
If the model is trained directly with the retrieval results, the model parameters will be inaccurate. If the image is recognized manually, the quality can be guaranteed but the efficiency is low.

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
  • Method, device and medium for acquiring face recognition model training data based on video
  • Method, device and medium for acquiring face recognition model training data based on video
  • Method, device and medium for acquiring face recognition model training data based on video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] According to the embodiment of the present application, an embodiment of a method for acquiring face recognition model training data based on video is also provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a set of computer-executable instructions such as and, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0047] The method embodiment provided in Embodiment 1 of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. figure 1 A hardware structure block diagram of a computer device (or mobile device) used in the method of the present application is shown. Such as figure 1 As shown, the computer device 10 (or mobile device 10) may include one or more processors (102a, 102b, ..., 102n are used in the figure to show that the p...

Embodiment 2

[0081] In an optional embodiment, the present application also provides a method for acquiring face recognition model training data based on video. The method can include:

[0082] Standard image processing step: acquiring two or more standard images from different angles of the person to be identified, performing face detection and key point extraction on the standard images respectively, and generating a first descriptor set;

[0083] Video processing step: for the video containing the person, extract the video frame, identify the human face part in the extracted video frame, and save the human face part as a human face picture;

[0084] Image comparison step: extracting key points from the face image, generating a second descriptor, calculating the distance between each first descriptor and second descriptor in the first descriptor set, and judging the person based on the distance Whether the face picture is the person to be recognized, so as to obtain the face recognition...

Embodiment 3

[0089] In an optional embodiment, the present application also provides a method for acquiring face recognition model training data based on video. The method can include:

[0090] Standard image processing step: acquiring two or more standard images of persons to be identified, performing face detection and key point extraction on the standard images respectively, and generating a first descriptor set;

[0091] Video processing step: for the video containing the person, extract the video frame, identify the human face part in the extracted video frame, and save the human face part as a human face picture;

[0092] Image comparison step: extracting key points from the face image, generating a second descriptor, calculating the distance between each first descriptor and second descriptor in the first descriptor set, and judging the person based on the distance Whether the face picture is the person to be recognized, so as to obtain the face recognition model training data.

...

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 application discloses a method, apparatus and medium for acquiring face recognition model training data based on video. The method comprises the following steps of: acquiring a standard picture of a person to be recognized; performing face detection and key point extraction on the standard picture to generate a first descriptor; for the video including the person, the video frame is extracted, the face part in the extracted video frame is recognized, and the face part is saved as a face picture; the key points of the face picture are extracted, a second descriptor is generated, thedistance between the first descriptor and the second descriptor is calculated, and whether the face picture is the person to be recognized is judged based on the distance, so as to obtain the face recognition model training data. This method can enrich the training data of face recognition model, reduce the workload of manual screening, and thus solve the problems of incomplete preparation of training data, single type, and great difficulty in cleaning.

Description

technical field [0001] The present application relates to the technical field of image data processing, in particular to a method and device for obtaining face recognition model training data from videos. Background technique [0002] The training of face recognition models, especially celebrity face recognition models, usually requires the preparation of a large amount of training data. Generally, each star training needs about 500 to 1000 pictures to achieve better accuracy. In addition, the star ranking changes very frequently, and the existing star recognition model needs to be continuously expanded or updated. This is a serious challenge for data preparation. [0003] There are usually two methods to find the training data of faces, especially the faces of celebrities, one is to collect in the network gallery, and the other is to take screenshots in film and television dramas. Either way, manual participation is required, and there are respective defects: the quality...

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): G06K9/00
CPCG06V40/168G06V40/172G06V20/40
Inventor 秦浩达
Owner BEIJING YINGPU TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com