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

A Method of Converting Gesture Recognition to Identity Recognition Based on Feature Transfer Learning

A technology of gesture recognition and identity recognition, which is applied in the direction of character and pattern recognition, instruments, biological neural network models, etc., can solve the problems of not considering user identity information, shorten the time of user identity recognition, improve performance, and have wide application prospects Effect

Active Publication Date: 2021-03-02
ANHUI UNIVERSITY OF TECHNOLOGY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This application adopts the method of incremental learning to identify the user's touch screen gesture habit to transparently authenticate the owner of the smartphone, which ensures the security of the authentication process, but the application also does not consider the user identity information contained in the gesture, although It has been able to meet the requirements of mobile phone user authentication, but there are still relatively large limitations in terms of the overall scheme

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 Method of Converting Gesture Recognition to Identity Recognition Based on Feature Transfer Learning
  • A Method of Converting Gesture Recognition to Identity Recognition Based on Feature Transfer Learning
  • A Method of Converting Gesture Recognition to Identity Recognition Based on Feature Transfer Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] combine figure 1 A method for converting gesture recognition to identity recognition based on feature transfer learning in this embodiment specifically includes the following steps:

[0050] Step 1. Create a gesture training set that includes both gesture type labels and user identity labels. The specific steps are as follows figure 2 As shown, namely:

[0051] The Microsoft Kinect v2 sensor is used to collect the user's dynamic gesture data, capture the three-dimensional position (x, y, z) sequence of 25 joints of the user's whole body, and obtain the joint data samples corresponding to the dynamic gesture. Among them, the 25 joints of the whole body are as follows: the end of the spine, the center of the spine, the neck, the head, the left shoulder, the left elbow, the left wrist, the left hand, the right shoulder, the right elbow, the right wrist, the right hand, the left hip, the left knee, the left ankle, the left Foot, right hip, right knee, right ankle, right ...

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 method for converting gesture recognition to identity recognition based on feature transfer learning, and belongs to the technical fields of pattern recognition and biological recognition. The main steps of the present invention include: step 1, making a gesture training set that includes both gesture type tags and user identity tags; step 2, constructing a gesture recognition network and a feature transfer network model; step 3, based on the produced data set, training gesture recognition Network; step 4, based on the produced data set, train the feature transfer network; step 5, transfer the network model parameters according to the learned features, input a dynamic gesture, and identify the corresponding user identity. The invention proposes a gesture recognition network based on a bidirectional threshold recurrent network, and uses a feature transfer network to convert gesture recognition to identity recognition, which has broad application prospects in the fields of information security, medical dust prevention, and the like.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and biological recognition, and more specifically relates to a method for converting gesture recognition to identity recognition based on feature transfer learning. Background technique [0002] With the rapid development of science and technology and information, social security and information security have shown unprecedented importance, and people urgently need some fast and effective identification technology as a security guarantee. According to the source of information, the existing identification technology can be divided into cryptographic technology based on password or mark and biometric technology based on biometric features. [0003] The password-based identification method judges the current user's login authority by identifying a set of user name-password combinations preset by the user, such as the login of electronic accounts such as mailboxes, WeChat, and blogs; 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): G06K9/00G06K9/62G06N3/04
CPCG06V40/28G06N3/045G06F18/214
Inventor 刘恒戴亮亮
Owner ANHUI UNIVERSITY OF TECHNOLOGY