Pet recognition method combining face and voiceprint

A recognition method and voiceprint recognition technology, which is applied in the field of convolutional neural network and face recognition, can solve the problems of not using voiceprint recognition, less research and application, etc., and achieve the effect of good performance experience and high recognition accuracy

Inactive Publication Date: 2018-11-02
ZHEJIANG UNIV OF TECH
View PDF11 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in these fields, there are few related researches and applications, and it is urgent for scientific researchers to develop
[0005] Patent No. 201410006204.6 and Patent No. 201611032333.8 each proposed a pet identification method, but both only involved image identification, and did not use voiceprint identification methods

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
  • Pet recognition method combining face and voiceprint
  • Pet recognition method combining face and voiceprint
  • Pet recognition method combining face and voiceprint

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The present invention will be further described below in conjunction with the accompanying drawings.

[0059] refer to figure 1 , figure 2 and image 3 , a pet recognition method combining face and voiceprint, comprising the following steps:

[0060] S1: Initialize the pet recognition classifier, including classifier structure initialization and classifier weight initialization;

[0061] S2: Obtain image data, obtain voiceprint data;

[0062] S3: classify and label data;

[0063] S4: voiceprint data processing;

[0064] S5: update the classifier iteratively;

[0065] S6: Determine whether the classifier meets the accuracy requirement, if yes, save the current parameters and end the program, if not, continue training.

[0066] In this example, the image data collected by oneself is classified and discriminated, and the method includes the following steps:

[0067] S1: Initialize the pet recognition classifier structure

[0068] In the experiment, the face recogni...

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

A pet recognition method combining a face and a voiceprint is provided. The method comprises the following steps: S1: initializing a pet recognition classifier, including classifier structure initialization and classifier weight initialization; S2: acquiring image data, and acquiring voiceprint data; S3: sorting and marking the data; S4: performing voiceprint data processing; S5: iteratively updating the classifier; and S6: determining whether the classifier meets the accuracy requirement, if so, saving the current parameter and ending the program, and if not, continuing the training. The method provided by the present invention combines two recognition methods of face recognition and voiceprint recognition, and has high recognition precision.

Description

technical field [0001] The present invention relates to convolutional neural network (Convolutional Neural Networks, CNN) and face recognition technology, wherein the convolutional neural network uses 2DCNN and 3DCNN, and the face recognition technology uses the FaceNet network structure and loss function calculation ideas for reference, and integrates facial recognition and voiceprint recognition, the two recognition methods are combined at the level of output results to obtain higher accuracy. Background technique [0002] With the continuous advancement of social technology and the urgent requirements for automatic identity verification in all aspects, biometric technology has developed rapidly in recent decades. As an inherent attribute of living things, biological characteristics have strong self-stability and individual differences, so they become the most ideal basis for automatic identity verification. Among many biometric technologies, facial recognition has more p...

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): G06K9/00G06N3/04G10L17/26G10L17/18G10L17/04
CPCG10L17/04G10L17/18G10L17/26G06V40/10G06N3/045
Inventor 宣琦任星宇刘毅徐东伟陈晋音
Owner ZHEJIANG UNIV OF TECH
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