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

Method for improving collective photo face recognition precision based on block amplification

A face recognition and group photo technology, applied in the field of face recognition, to achieve the effect of improving performance efficiency, reducing performance pressure, and improving accuracy

Pending Publication Date: 2021-06-18
广东图友软件科技有限公司
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for improving the accuracy of face recognition in group photos based on block enlargement, so as to improve the accuracy and completeness of face retrieval in file retrieval and utilization, and improve file management and utilization levels

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 for improving collective photo face recognition precision based on block amplification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] This embodiment proposes a method based on sub-block enlargement to improve the face recognition accuracy of group photos, so as to improve the possibility of face feature information being extracted in electronic files such as group photos and graduation photos with a large number of people. and quality, to achieve the effect of complete person identification. In this embodiment, the implementation method of improving the face recognition accuracy of the group photo based on block enlargement is as follows:

[0044] A. When the system detects that the number of people in the file photo is relatively large (more than 50 people) and the file is relatively large (more than 10M), according to the resolution level of the photo, it will be processed by splitting into two, splitting into four or splitting into eight pieces;

[0045] B. Intercept the photo file into multiple pieces and save them independently;

[0046] C. According to the scanning order from left to right, each...

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 method for improving collective photo face recognition precision based on block amplification, and the method comprises the steps: carrying out the block interception of a recognition object into a plurality of small blocks, carrying out the local amplification of the small blocks, and enabling a face recognition module to carry out the recognition and face feature information extraction. Through the application of the method, the problems that the number of recognized faces is incomplete and the recognition precision is not enough when face retrieval is carried out on photos such as collective photos and graduation photos with a large number of people can be solved. The photo is amplified and then recognized, so that the possibility and quality of extracting the face feature information can be improved, and a relatively complete person recognition effect is realized; according to the method for improving the collective photo face recognition precision through block amplification, the face recognition performance and efficiency can be improved, meanwhile, the face recognition precision is improved, a brand new technical means is provided for intelligent and accurate retrieval of archive management departments, and the service level of the archive management departments can be improved.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a method for improving the face recognition accuracy of a group photo based on block enlargement. Background technique [0002] At present, face recognition technology has been applied to all aspects of society, and the technology application is relatively mature. Face recognition can simplify identity authentication and other issues. However, this technology still has some shortcomings in the recognition of photos such as group photos and graduation photos of a large number of people (more than 50 people). Many mature face recognition manufacturers on the market (such as Redsoft, Baidu, Google, etc.) often have problems of incomplete recognition and insufficient recognition accuracy when targeting such super-many photos of people. Recognition technology is difficult to fully use. Since the face recognition technology involves a large number of calculations when it inv...

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): G06K9/00G06N3/04
CPCG06V40/172G06V40/168G06N3/045
Inventor 汤进军李贺郑业盛
Owner 广东图友软件科技有限公司
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