Sample collection method and system used for face recognition and based on video

A face recognition and sample collection technology, applied in the field of face recognition, can solve the problems of slow speed, low efficiency, and long time consumption, and achieve the effect of fast speed and high efficiency

Active Publication Date: 2015-03-25
SUZHOU KEDA TECH
View PDF5 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] For this reason, the technical problem to be solved by the present invention is that the video-based face recognition sample collection method in the prior art is slow, time-consuming and inefficient, thus proposing a video-based face recognition sample collection method and system

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
  • Sample collection method and system used for face recognition and based on video
  • Sample collection method and system used for face recognition and based on video
  • Sample collection method and system used for face recognition and based on video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] This embodiment provides a video-based face recognition sample collection method, such as figure 1 shown, including the following steps:

[0082] S1: Obtain the image area with motion information in the image frame of the video, such as figure 2 shown, including:

[0083] First use the initial image frame of the video to establish the background model of each pixel or pixel area, and the initial image frame can select the first frame or the first three frames.

[0084] Build a foreground model for each pixel or pixel region in the current image frame.

[0085] Computes the difference between the background model and the foreground model for each pixel or region of pixels.

[0086] Determine a preset threshold of 20*20 pixels. If the connected area of ​​the pixel region that produces the difference is smaller than the preset threshold, it means that the current frame image does not generate motion information, and there is no human face. Delete the impossible to gene...

Embodiment 2

[0111] This embodiment provides a video-based face recognition sample collection method. The topological diagram of face recognition sample collection information network is as follows: Image 6As shown, according to the functions, there are mainly three parts: the acquisition front-end, the back-end server and the client management end. There are two types of acquisition front-ends: ordinary acquisition front-end 1 and intelligent acquisition front-end 2. Front-end processor 3 outputs front-end video files, ordinary acquisition front-end 1 outputs encoded video images, and the output of intelligent acquisition front-end 2 includes part of the data extracted by intelligent front-end. Face information specifically refers to information in the form of condensed video frames, face capture area images, or face feature data. The back-end server comprises a first server 4 and a second server 5. The first server 4 carries out face feature extraction with the video collected by the f...

Embodiment 3

[0125] This embodiment provides a video-based face recognition sample collection system, such as Figure 8 shown, including:

[0126] An image area acquisition module, configured to acquire an image area with motion information in an image frame of a video;

[0127] A face detection module, configured to detect the image region to obtain a face pixel region;

[0128] The face tracking module is used to track the face pixel area in the image frame containing the face, and obtain the historical image frame of the same face;

[0129] The face feature acquisition module is used to extract the face features from the historical image frames of the same face with high quality, and obtain the required face features for face recognition;

[0130] The face feature storage module is used to store the face feature.

[0131] The image area acquisition module includes:

[0132] Background model establishment sub-module, for utilizing the initial image frame in the video to establish bac...

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 provides a sample collection method and system used for face recognition and based on a video. The sample collection method used for face recognition and based on the video comprises the steps that an image region, containing movement information, in an image frame of the video is obtained firstly, the image region is detected so that a face pixel region can be obtained, the face pixel region in the image frame containing the face is tracked, so that a historical image frame of the same face is obtained, face characteristic extraction is conducted on the high-quality historical image frame of the same face, so that face characteristics required for face recognition are obtained, and finally, the face characteristics are stored. According to the sample collection method and system used for face recognition and based on the video, manual operation of sample collection workers is not needed in the whole sample collection process for face recognition, the collection speed is high, and the collection efficiency is high.

Description

technical field [0001] The present invention relates to the technical field of face recognition, in particular to a video-based face recognition sample collection method and system. Background technique [0002] Face recognition is not only a research hotspot in the field of artificial intelligence, but also has important practical significance in the field of public security. Face recognition technology includes face image sample collection, sample image preprocessing, classifier training, and sample recognition. The sample collection work is the cornerstone of face recognition, and its significance is self-evident. [0003] The collection of face recognition samples used to be based on images. For example, let the volunteers be at a certain shooting point sequentially and orderly; then, the sample collection workers take multiple shots of the volunteers according to the differences in posture, lighting, expression, etc.; Screening and processing to establish a face recog...

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): G06K9/00G06K9/20
CPCG06V40/161G06V40/168
Inventor 鄢展鹏姜莎张泉张震国晋兆龙陈卫东
Owner SUZHOU KEDA TECH
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