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

Quick retrieval method and device of face recognition

A face recognition and fast technology, applied in the field of face recognition, can solve the problems of large retrieval calculation, low efficiency, large sample size, etc., and achieve the effect of high retrieval efficiency, wide application range, and reduced data volume.

Active Publication Date: 2016-07-27
智慧眼科技股份有限公司
View PDF6 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a fast retrieval method and device for face recognition to solve the existing technical problems of large amount of retrieval operations and low efficiency due to the large sample size of the feature database for face recognition

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
  • Quick retrieval method and device of face recognition
  • Quick retrieval method and device of face recognition
  • Quick retrieval method and device of face recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0037] refer to figure 1 , a preferred embodiment of the present invention provides a fast retrieval method for face recognition, the method comprising:

[0038] Step S101, establish a sample database, extract the feature data of the cropped face image based on the deep learning (Deep Learning) algorithm to obtain sample data, and perform binary conversion and Hash mapping of the sample data to multiple Hash tables;

[0039] In this embodiment, all extracted sample features are binarized with the sign bit or the mean value as the threshold, and the matched sample ID information is stored in multiple Hash tables according to multiple Hash functions.

[0040] Step S102, perform binary conversio...

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 quick retrieval method and device of face recognition. The method comprises the following steps: establishing a sample database, carrying out binaryzation transformation on sample data, and carrying out Hash mapping on the sample data into a plurality of Hash tables; in the same way, carrying out the binaryzation transformation on the characteristic data of a sample to be queried, and utilizing Hash function projection adopted by establishing the sample database to obtain a binary code queue, and extracting matched samples in the plurality of Hash tables from the corresponding buckets of the Hash tables to carry out merge sort; calculating a Hamming distance between the binary characteristics of the sample to be queried and the binary characteristics of an effective sample subjected to the merge sort; and carrying out 1:1 accurate comparison on the effective sample of which the Hamming distance is smaller than a set threshold value and the sample to be queried to obtain most similar sample data. Through hierarchical query, a retrieval amount is drastically reduced, a floating point calculated amount is greatly reduced, and retrieval efficiency is high. In addition, the retrieval scheme has the advantages of high adaptation, wide application range and good popularization value.

Description

technical field [0001] The present invention relates to the field of face recognition, in particular, to a fast retrieval method and device for face recognition. Background technique [0002] In the field of face recognition, such as the public security system and social security system, the face feature database involved may reach tens of millions or hundreds of millions of targets. If an unknown face is input and who is queried in the database, if according to the traditional The 1:1 comparison of features using this method requires hundreds of millions of comparisons, which is very inefficient. Therefore, it is urgent to design a face recognition retrieval method and device with high retrieval efficiency. Contents of the invention [0003] The present invention provides a fast retrieval method and device for face recognition to solve the existing technical problems of large amount of retrieval calculations and low efficiency due to the large sample size of a feature da...

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): G06F17/30
CPCG06F16/583
Inventor 廖欢杨东
Owner 智慧眼科技股份有限公司
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