A face retrieval method and system based on class center

A retrieval system and face technology, applied in still image data retrieval, biological neural network model, still image data query, etc., can solve the problem of no online incremental update method, lack of approach to the center of gravity, poor search accuracy, etc. problem, to achieve the effect of improving system accuracy, reducing system misrecognition rate, and increasing class distance

Active Publication Date: 2021-07-13
CHENGDU KOALA URAN TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] 1. In addition to the average processing, the invention lacks a further approach to the center of gravity, resulting in poor search accuracy;
[0007] 2. There is no online incremental update method, and there are certain defects

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
  • A face retrieval method and system based on class center
  • A face retrieval method and system based on class center
  • A face retrieval method and system based on class center

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] In order to make the object, technical solution and advantages of the present invention clearer, the following in conjunction with specific embodiments and description Figure 1-Figure 3 , the present invention will be described in further detail. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0050] A kind of face retrieval method based on class center provided by the present invention comprises registration face database method and face retrieval and online update feature database method, described registration face database method, comprises the following steps:

[0051] S1. Step 1: Input m pictures of the same person, and use a deep neural network to e...

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 retrieval method based on a class center, including a face database registration method and a face retrieval and online update feature database method; The noise introduced by the impact of shooting between different photos significantly increases the class distance, reduces the system misrecognition rate, and effectively reduces the intra-class distance between all photos of the same natural person, which significantly improves the system accuracy. The class center / gravity center is adopted, so the time complexity of the retrieval algorithm is fixed at O(N), and it is not affected by the number of photos in the face database. A method for online incremental update of the class center / gravity center is further proposed, which significantly strengthens the system adaptation. sex.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and more specifically relates to a face retrieval method based on a class center. At the same time, the invention also relates to a face retrieval system based on the class center. Background technique [0002] Face recognition: Extract feature vectors from face photos. At present, the similarity between photos is generally measured according to the angle between feature vectors, so as to determine whether the two belong to the same natural person. [0003] Face retrieval: also known as 1:N face recognition mode, or identification. The face database contains M photos of N natural persons (M≥N), and each natural person has more than or equal to 1 photo. For retrieving photos, check whether the similarity of the photo with the highest similarity in the face database is greater than the threshold, so as to determine the identity of the person. [0004] Through preliminary inquiry, no simila...

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 Patents(China)
IPC IPC(8): G06F16/53G06N3/04
Inventor 贾可奚兴张艳明沈复民申恒涛
Owner CHENGDU KOALA URAN TECH CO LTD
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