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

Single sample face recognition method and system based on facial feature points

A technology of facial features and feature points, applied in the field of computer vision and pattern recognition

Active Publication Date: 2019-12-03
SHENZHEN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a single-sample face recognition method and system based on facial feature points, aiming to solve the problem that the current single-sample face recognition algorithm has limitations

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
  • Single sample face recognition method and system based on facial feature points
  • Single sample face recognition method and system based on facial feature points
  • Single sample face recognition method and system based on facial feature points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0077] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0078] Based on the above problems, the present invention provides a single-sample face recognition method based on facial feature points.

[0079] refer to figure 1 , figure 1 It is a schematic flowchart of the first embodiment of the face feature point-based single-sample face recognition method of the present invention.

[0080] In this embodiment, the single-sample face recognition method based on facial feature points includes:

[0081] Step S10, acquiring a face image to be recognized;

[0082] In this embodiment, a face image to be recognized is input into a face recognition device or a face recognition system, and the face image to be recognized can be a standard face image, such as an electronic passport face image and a driver's license Face images, or non-standard face images, such as face images with d...

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 single-sample face recognition method and system based on facial feature points. The method includes: acquiring a face image to be recognized; collecting feature points in the face image to be recognized, and the feature points include key points and dense points ; extract the feature vector of the feature point; initialize the weight of the feature point and the first projection matrix; calculate the weighted cooperative representation of the feature vector to obtain the representation coefficient of the feature vector; judge whether to update the weight of the feature point and the first projection Matrix; if so, after calculating the collaborative representation error of the feature vector according to the representation coefficient, update the weight of the feature point and the first projection matrix according to the collaborative representation error, and return to recalculate the weighted collaborative representation of the feature vector; if not , then determine the identity ID of the face image to be recognized according to the weight, the first projection matrix and the feature vector. The invention can increase the robustness of the algorithm, improve the recognition rate of the human face and reduce the computational complexity of the recognition.

Description

technical field [0001] The invention relates to the technical fields of computer vision and pattern recognition, in particular to a single-sample face recognition method and system based on facial feature points. Background technique [0002] As a research hotspot in computer vision and pattern recognition, face recognition has received a lot of attention due to its advantages of non-contact and naturalness (such as identifying people similar to human eyes) and huge industry value (such as identification, human-computer interaction, etc.). wide attention in academia and industry. In the process of face recognition, there may be large differences in the face images taken by the same person in different environments. It may cause a large difference between face images. Especially when there is a large difference between the face image to be recognized and the face image in the query database, the face to be recognized can be accurately determined only on the premise that the...

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): G06K9/00
CPCG06V40/171G06V40/168
Inventor 杨猛王兴沈琳琳
Owner SHENZHEN UNIV