Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

An efficient face feature value retrieval method and system based on faiss

A face feature and feature value technology, applied in the field of face recognition, can solve the problems of consuming more time and resources, and achieve the effect of speeding up the retrieval speed

Active Publication Date: 2019-05-03
小视科技(江苏)股份有限公司
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] When there is a lot of data in the face database, it takes more time and resources to compare face feature values

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
  • An efficient face feature value retrieval method and system based on faiss
  • An efficient face feature value retrieval method and system based on faiss
  • An efficient face feature value retrieval method and system based on faiss

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to better understand the technical content of the present invention, specific embodiments are given together with the attached drawings for description as follows.

[0054] Aspects of the invention are described in this disclosure with reference to the accompanying drawings, which show a number of illustrated embodiments. Embodiments of the present disclosure are not necessarily defined to include all aspects of the present invention. It should be appreciated that the various concepts and embodiments described above, as well as those described in more detail below, can be implemented in any of numerous ways, since the concepts and embodiments disclosed herein are not limited to any implementation. In addition, some aspects of the present disclosure may be used alone or in any suitable combination with other aspects of the present disclosure.

[0055] combine figure 2 , image 3 , the present invention proposes a method for efficient face feature value retr...

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 an efficient face feature value retrieval method and system based on faiss. A face retrieval module is developed based on an AI similarity search tool of faiss-facebook open source, the unique identifier of the face image with the highest similarity comparison score with the face feature value to be compared and the corresponding comparison score are retrieved from the facefeature value storage module, and then retrieval result judgment is executed to accelerate the retrieval speed of the face feature value; Meanwhile, in the retrieval process, the face feature value library is continuously optimized, the face image with the high repetition degree is reduced, and the face image with the best typicality is selected.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a method and system for efficient face feature value retrieval based on faiss. Background technique [0002] Face recognition refers to the extraction of feature values ​​from face images, and comparison with other face feature values, and the highest comparison score is taken. If the highest comparison score exceeds the set threshold, the two faces are considered to be the same. the same person. The process of implementing face recognition is as follows: figure 1 ,specific: [0003] The first step is to create a face library and set the capacity and threshold of the face library. [0004] The second step is to add face photos in the bottom database to the face database, extract feature values ​​from the face photos in the bottom database, and store the face feature values ​​in the face database. [0005] The third step is to submit the photo of the face to be recogn...

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
IPC IPC(8): G06K9/00G06K9/62G06F16/53
Inventor 杨帆曹赛男
Owner 小视科技(江苏)股份有限公司
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
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