Unlock instant, AI-driven research and patent intelligence for your innovation.

Face image clustering method, device and equipment and computer readable storage medium

A face image and clustering method technology, which is applied in the field of face image clustering, can solve problems such as poor clustering ability of face image clustering technology, and achieve poor clustering ability, low computational complexity, and high clustering The effect of class performance

Active Publication Date: 2021-11-12
SHENZHEN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The main purpose of the present invention is to provide a face image clustering method, device, equipment and computer-readable storage medium, aiming to solve the technical problem of poor clustering ability of face image clustering technology

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 clustering method, device and equipment and computer readable storage medium
  • Face image clustering method, device and equipment and computer readable storage medium
  • Face image clustering method, device and equipment and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0086] Based on the first embodiment, the second embodiment of the face image clustering method of the present invention is proposed. In this embodiment, step S10 includes:

[0087] Step S11: When updating the base matrix, deep coefficient matrix and activation function parameters of the fully connected neural network in sequence, obtain the deep coefficient matrix, and input the deep coefficient matrix to the fully connected neural network, so that the deep coefficient matrix As the input of the fully connected neural network;

[0088] Step S12: (1) Fix the deep coefficient matrix and the activation function parameters, and based on the deep coefficient matrix, the activation function parameters of the fully connected neural network and the face training image, through the backpropagation neural network The network algorithm updates the base matrix of the fully connected neural network from back to front until iterating the first preset number of steps;

[0089] Step S13: (2...

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 clustering method, device and equipment and a computer readable storage medium, and the method comprises the steps of obtaining a face training image from a face database, and carrying out the updating of all layers of basis matrixes, deep coefficient matrixes and activation function parameters of a full-connection neural network in turn based on the face training image; after the basis matrix, the deep coefficient matrix and the activation function parameters are updated, obtaining a BP-DGNMF model; obtaining a to-be-clustered face image, and inputting the to-be-clustered face image into the BP-DGNMF model to determine a deep feature set corresponding to the to-be-clustered face image; and based on the deep feature set, performing clustering operation on the to-be-clustered face image to obtain a clustering result corresponding to the to-be-clustered face image. According to the invention, the basis matrix, the deep coefficient matrix and the activation function parameters of the full-connection neural network are updated in turn, and the BP-DGNMF model with high clustering performance and low calculation complexity is constructed.

Description

technical field [0001] The present invention relates to the technical field of face image clustering, in particular to a face image clustering method, device, equipment and computer-readable storage medium. Background technique [0002] With the advent of the information age, the identification and verification of personal identity using the inherent physiological and behavioral characteristics of the human body has become more and more popular. With the promotion of the application of face recognition and retrieval systems, the face image data in the system has increased dramatically, and the face clustering technology has become an important basis for improving the retrieval efficiency of the system. Face clustering usually clusters the face image information in the database into some different sub-categories, so that the similarity between the sub-categories is as small as possible, and the similarity within the sub-categories is as large as possible. The subcategories w...

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): G06K9/62G06K9/00G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F18/23213Y02D10/00
Inventor 陈文胜占子豪
Owner SHENZHEN UNIV