Face and voiceprint authentication system and method based on deep transfer learning

A technology of transfer learning and authentication system, applied in the field of artificial intelligence applications, can solve the problems of wasting user time, unrealistic collection, etc., to achieve the effect of improving accuracy, improving security and confidentiality, and improving the starting point of training

Pending Publication Date: 2020-09-29
SHANGHAI WULING SHENGTONG INFORMATION TECH CO LTD
View PDF1 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the user's face and voiceprint are registered, it is unrealistic to collect a

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 and voiceprint authentication system and method based on deep transfer learning
  • Face and voiceprint authentication system and method based on deep transfer learning
  • Face and voiceprint authentication system and method based on deep transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0071] Deep learning algorithms can extract high-level abstract feature attributes of images layer by layer. The CNN model belongs to a model of deep learning algorithm. Applying the CNN model to the recognition task of face and voiceprint can realize the automatic extraction of image features of face and voiceprint.

[0072] With the help of transfer learning algorithm, the pre-training model learned from other large data sets can be reused in related fields after perfect modification, which can largel...

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 provides a face and voiceprint authentication system and method based on deep transfer learning. The face and voiceprint authentication system comprises: a user side module used for collecting and constructing a human face and voiceprint image data set and returning a verification result; a training module whichcomprises a data preprocessing algorithm, a user living body detection algorithm, construction of a deep convolutional neural network model, fusion of a transfer learning algorithm, training of the convolutional neural network model and a model integration algorithm of theconvolutional neural network; and the data and model storage module comprises storage of a face data set and a voiceprint data set and storage of a face recognition model and a voiceprint recognitionmodel which are trained by the network model. According to the invention, face recognition and voiceprint recognition are applied to the system verification process, a user does not need to input a user name and a password and other operations, so that the system login process is simpler and more convenient, the user does not need to worry about the problem that the user name and the password arestolen and forgotten, and the login experience of the user is improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence applications, in particular to a face and voiceprint authentication system and method based on deep transfer learning. Background technique [0002] The traditional identity authentication method is to use the user name and password to register and log in. In this authentication method, when the user forgets the user name and password, the user needs to retrieve the password to re-authenticate, which is not conducive to the user's login verification experience. The login method based on face and voiceprint does not need to worry about forgetting the user name and password, just scan the face and perform voiceprint authentication in real time. [0003] At present, most intelligent identity authentication methods adopt a single authentication method of face or voiceprint, which is not conducive to the security and confidentiality of system authentication. The user collects a piece o...

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
IPC IPC(8): G06K9/00G06K9/62G06F21/32G06N3/04G06N3/08
CPCG06F21/32G06N3/084G06V40/165G06V40/171G06V40/172G06N3/045G06F18/25
Inventor 王敬贤卢强储昭兵陈岳军徐源
Owner SHANGHAI WULING SHENGTONG INFORMATION 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