Face image tag data generating system and method

A technology of labeling data and face images, applied in the field of face recognition, can solve the problem of low accuracy of heterologous recognition, and achieve the effect of automatic search and tracking, rich face recognition scenes, and rich standard face sources.

Active Publication Date: 2018-07-31
一石数字技术成都有限公司
View PDF9 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a face image label data generation system and its method to solve the problem of low accuracy of heterogeneous recognition in view of the above existing problems

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 image tag data generating system and method
  • Face image tag data generating system and method
  • Face image tag data generating system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] All features disclosed in this specification, or steps in all methods or processes disclosed, may be combined in any manner, except for mutually exclusive features and / or steps.

[0049] Any feature disclosed in this specification (including any appended claims, abstract), unless otherwise stated, may be replaced by alternative features that are equivalent or serve a similar purpose. That is, unless expressly stated otherwise, each feature is one example only of a series of equivalent or similar features.

[0050] Such as figure 1 and 2 As shown, the first embodiment discloses a human face image label data generation system, which includes: image acquisition devices 101, 102, and 103 with three pixel levels (other number of pixel levels are the same), used for a single acquisition of the same The face data of three pixel levels of benchmark person 10, the three pixel levels are: 1 million to 5 million (excluding) pixels, 5 million to 10 million (excluding) pixels, and...

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 image tag data generating system and method. The system comprises: image capture devices with a plurality of pixel levels, a tag data generating device and a face device. The method comprises: collecting the face data with different pixel levels of the same person to further screen out a predetermined number of clear face frame images, extracting feature values fromthe selected face frame images, and further storing the feature values corresponding to the tag data of the person; when identifying the face, according to the device information of the capture deviceof the face image to be recognized, providing a face feature value set with corresponding pixel levels for comparison, and outputting the corresponding tag data after passing the comparison, whereinthe face data and the face data to be recognized are short videos or pictures and the tag data is personal identity information. The system or method of the invention can completely solve the problemof poor accuracy of heterogeneous face recognition, improve the accuracy of existing face recognition, and achieve full pixel compatibility with existing security monitoring devices.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a face image tag data generating system and method thereof. Background technique [0002] After years of research and development, face recognition technology has become increasingly mature. It can be seen that the face image recognition system based on deep learning has been widely used in finance, security, identity authentication and other industries. However, in my country, there are many types of imaging equipment, and the mainstream ones are distinguished by pixels: 1 million pixels, 2 million pixels, etc. Pixels, 3 million pixels, 5 million pixels, 7 million pixels, 10 million pixels or more, etc. Considering the reason of storage capacity, currently in the security industry, most cameras with 2 megapixels are used. [0003] The existing face recognition algorithm basically uses the face collected by the same level of pixels for dynamic identity recognition. Faces capture...

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
CPCG06V40/168G06V40/172
Inventor 卢荣新王泽民李珉施国鹏
Owner 一石数字技术成都有限公司
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