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

Face recognition architecture design method based on edge calculation and cloud overall planning

A face recognition and architecture design technology, applied in computing, computer components, neural learning methods, etc., can solve problems such as data transmission and deep model training, and achieve fast response time, high accuracy, and improved accuracy.

Inactive Publication Date: 2019-09-03
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A large amount of portrait monitoring data can provide a good foundation for deep learning network training, but it also brings problems in data transmission and deep model training

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 recognition architecture design method based on edge calculation and cloud overall planning
  • Face recognition architecture design method based on edge calculation and cloud overall planning
  • Face recognition architecture design method based on edge calculation and cloud overall planning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0048] The technology of network architecture design in this embodiment mainly involves the following types of technologies: 1) Edge computing technology: use edge computing technology to make task response close to the data front end, reducing response delay; 2) cloud-based face recognition architecture: joint The local models of multiple edge nodes can train the joint model by constructing an autoencoder to improve the recognition accuracy.

[0049] The network architecture design is based on the TensorFlow framework and the Pycharm development environment: the TensorFlow framework is a development framework based on the python language, which can easily and quickly build a reasonable deep learning network, and has good cross-platform interaction capabilities. TensorFlow provides many encapsulation functions in the deep learning architecture and interfaces of various image processing functions, including OpenCV-related image processing functions. The TensorFlow framework can...

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 face recognition architecture design method based on edge calculation and cloud overall planning. The method comprises an edge node model training step of designing the corresponding lightweight deep learning networks in different region points according to the concept of edge calculation, and carrying out local model training; a data and model transmission step of uploading a corresponding model result according to a calculation result of the multi-stage edge node; a cloud model training step of performing training learning on the uploaded data and the model in a cloud overall planning mode to obtain a global face recognition model; and a task final feedback step. According to the invention, the edge computing technology and the cloud overall planning form are applied to the face recognition task under the big data to construct the face recognition architecture with fast response time and high accuracy, and the basic task is placed at the front end of the data to be processed, so that the response delay caused by data transmission is reduced; and the local model of each edge node is integrated, so that the overall face recognition accuracy is improved.

Description

technical field [0001] The invention relates to the field of deep learning application technology, in particular to a face recognition architecture design method based on edge computing and cloud coordination. Background technique [0002] In recent years, video surveillance has been popularized in large and medium-sized cities across the country, and has been widely used in the construction of social security prevention and control systems, and has become a powerful technical means for public security organs to investigate and solve crimes. Especially in mass incidents, major cases and double robbery cases, evidence clues obtained from video surveillance videos play a key role in the rapid detection of cases. In order to fully grasp the behavior trajectory of key personnel, it is necessary to build a large number of portrait checkpoints in key areas of counties and cities in the province, such as railway stations and bus stations. Therefore, a large amount of image data is ...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/08G06V40/16G06F18/214
Inventor 谢巍余孝源陈定权周延
Owner SOUTH CHINA 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