Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Pet face recognition method

A technology for facial recognition and pets, applied in biometric recognition, character and pattern recognition, computer components, etc., can solve the problems of low recognition accuracy and achieve high recognition accuracy, good performance experience, and good application prospects

Inactive Publication Date: 2018-11-23
ZHEJIANG UNIV OF TECH
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the shortcomings of the low recognition accuracy of the existing pet recognition methods, and to realize the function of accurately identifying individual pets in large quantities, the present invention proposes a pet face recognition method with high recognition accuracy

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 face recognition method
  • Pet face recognition method
  • Pet face recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further described below in conjunction with the accompanying drawings.

[0062] refer to Figure 1 ~ Figure 3 , a pet face recognition method, comprising the following steps:

[0063] S1: Initialize the pet face classifier, that is, use your own data set to train the weight parameters of the classifier. This method uses the FaceNet classifier structure, and the pre-trained model published by the FaceNet author is used as the initial weight parameter;

[0064] S2: Obtain image data through two methods of web crawler and field camera collection;

[0065] S3: classify and label the collected image data, and divide the image data into a training set and a test set in proportion;

[0066] S4: Perform face alignment operation on the collected image data;

[0067] S5: Update the iterative classifier, select training set batches according to the triplet principle of the FaceNet loss function and send them to the network for training;

[0068] S...

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 pet face recognition method. The method comprises the following steps: S1, initializing a pet face classifier, wherein the initialization comprises classifier structure initialization and classifier weight initialization; S2, acquiring image data, collecting through a web crawler and a real-time camera; S3, classifying and marking the data; S4, performing face alignment on the image data; S5, iteratively updating the classifier; and S6, judging whether the classifier meets a precision requirement, if the classifier meets the precision requirement, saving the current parameter and ending the program; if the classifier does not meet the precision requirement, continuing the training. The method disclosed by the invention is suitable for identifying the individual from batch of pets, and has high precision.

Description

technical field [0001] The present invention designs deep neural volumes and network deep convolutional neural networks (Convolutional NeuralNetworks, CNN) and face recognition technology, wherein the face recognition technology uses the FaceNet network structure and loss function calculation ideas for reference, and collects a large number of pet picture data sets in the original Fine-tuning and testing were carried out on the basis of the network, and higher accuracy was obtained. 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 prominent dire...

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): G06K9/00A01K29/00
CPCA01K29/005G06V40/172G06V40/168G06V40/10
Inventor 宣琦任星宇陈晋音刘毅徐东伟
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com