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

Face recognition method based on deep learning multi-layer non-negative matrix factorization

A technology of non-negative matrix decomposition and deep learning, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as no solution, deep learning performance degradation, etc., and achieve the effect of improving the face recognition rate

Active Publication Date: 2020-07-10
XIDIAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practical applications, the appearance changes caused by factors such as head pose, lighting, occlusion, etc. will lead to the performance degradation of deep learning, so far there is no good solution

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 recognition method based on deep learning multi-layer non-negative matrix factorization
  • Face recognition method based on deep learning multi-layer non-negative matrix factorization
  • Face recognition method based on deep learning multi-layer non-negative matrix factorization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] refer to figure 1 , the face recognition steps of the present invention based on deep learning multi-layer non-negative matrix factorization are as follows:

[0020] Step 1, obtain the feature data X(k) of each channel data of the training sample.

[0021] (1a) Obtain face dataset V train As a training data set, the total number of training samples in the training data set is n, the number of categories in the training data set is c, each training sample in the training data set is equally divided into K regions, and each region is used as 1 of the training samples channel data, and the training samples contain K channel data in total;

[0022] (1b) According to the training data set, under the Linux operating system, use the Caffe deep learning framework to fine-tune the parameters of the VGG-Face deep convolutional neural network;

[0023] (1c) Input each channel data of each training sample in the training data set into the VGG-Face deep convolutional neural netwo...

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 recognition method based on deep learning multi-layer non-negative matrix decomposition, which mainly solves the problem of low recognition rate of the existing face recognition technology under complex appearance changes. The technical solution is: 1. Use VGG-Face to extract the characteristic data of each channel data of the training sample and the test sample; 2. Repeat L times of normalization, nonlinear transformation and matrix decomposition for the characteristic data of each channel data of the training sample The feature extraction process obtains low-rank robust features; 3. Constructs K nearest neighbor classifiers; 4. Projects the feature data of each channel data of the test sample to obtain the projection coefficient vector; 5. Inputs the projection coefficient vector to Classification by K nearest neighbor classifiers; 6. Synthesize the classification results of K nearest neighbor classifiers to obtain the identification result of the test sample. The invention improves the face recognition rate under complex appearance changes, and can be applied to the fields of identification and information security.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a face image recognition method, which can be applied to the fields of identification and information security. Background technique [0002] With the continuous development of human society, face recognition has been widely used in security, finance, e-government and many other fields. Improving the performance of face recognition is conducive to expanding the application of face recognition. The current main research on face recognition is to extract effective, robust and more discriminative features and design classifiers with better classification ability. Selecting more robust and discriminative features and designing a classifier with good classification ability are the keys to improve the robustness of face recognition. [0003] Non-negative matrix decomposition is a feature extraction method for matrix decomposition under non-negative constraints. It has good 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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/172G06V40/168G06N3/045G06F18/24147G06F18/214
Inventor 同鸣李明阳陈逸然席圣男
Owner XIDIAN UNIV