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

Mass face library retrieval method based on man-machine collaboration

A human-machine collaboration and mass-person technology, applied in the field of massive face library retrieval based on human-computer collaboration, can solve problems such as unreachable retrieval results, gaps in advanced semantic features, and similar face distinction, and achieve robust face images Retrieval, the effect of significant application value

Pending Publication Date: 2021-06-11
HANGZHOU DIANZI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is a gap between the low-level features extracted by computer vision and the high-level semantic features captured by human vision, so the retrieval results of computer vision are far from meeting human expectations.
Face images have little difference in low-level contour features, and it is difficult to distinguish similar faces only by computer vision

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
  • Mass face library retrieval method based on man-machine collaboration
  • Mass face library retrieval method based on man-machine collaboration
  • Mass face library retrieval method based on man-machine collaboration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The present invention will be further described below in conjunction with accompanying drawing.

[0063] Such as figure 1 As shown, a massive face library retrieval method based on human-machine collaboration, specifically includes the following steps:

[0064] Step 1: Preprocessing of Pedestrian Surveillance Video

[0065] A number of surveillance videos from different corners of the campus were randomly selected, and the frame rate of the surveillance video was 60 frames per second; 2 frames per second were selected from the surveillance video for analysis, and the Retinaface model was used to detect the faces and key points of their facial features, and then Face alignment is carried out through facial feature key points; use the Arcface model to maximize the face classification interface in the angle space, and perform face recognition to extract face feature vectors, specifically:

[0066] Step 1-1: In order to improve the video face detection speed, perform fram...

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 massive face image library retrieval method based on man-machine collaboration. The low-level features extracted by computer vision are different from the high-level semantic features captured by human vision, so that the computer vision retrieval result cannot reach the expectation of people. Face images are small in difference in low-level contour features, and similar faces are difficult to distinguish only depending on computer vision. The method comprises the following steps: 1, establishing an image library; 2, training an EEG classification model by using an EEG signal generated by watching the portrait by a person; and 3, performing online iteration by using an EEG classification model, and retrieving a target image required by the testee from the image data. The face image retrieval method is different from a traditional face retrieval method, fast, accurate and robust massive face image retrieval is achieved by combining the powerful cognitive ability of the human brain with the fast computing ability and the massive storage ability of a computer, and the face image retrieval method has remarkable application value.

Description

technical field [0001] The invention belongs to the intersecting technical field of rapid sequence visual presentation and image retrieval, and in particular relates to a method for retrieving a massive face library based on human-machine collaboration. Background technique [0002] The existing video surveillance system only realizes the simple video storage function, and the efficient analysis and utilization of surveillance video information is still a problem. Therefore, in the video surveillance capture and recording of high-definition images, it provides identification, comparison, query to Designating human faces is the goal pursued by the new generation of video surveillance, and it is also an urgently needed function in practical applications. The rapid increase in the number of face images that can be obtained in the field of public security makes the existing face image retrieval technology face severe challenges in the process of processing massive image data. ...

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): G06K9/00G06K9/62G06N3/04G06F16/532
CPCG06F16/532G06V40/165G06V40/171G06V40/172G06V20/46G06V20/52G06N3/045G06F2218/02G06F18/22G06F18/214Y02D10/00
Inventor 孔万增胡宏洋徐森威
Owner HANGZHOU DIANZI UNIV
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