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

Parallel and distributing type identifying human face based on net

A distributed and grid technology, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as increased resource consumption, heavy computing workload, massive storage, and sensitivity to changes in light intensity

Inactive Publication Date: 2006-08-23
BEIJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] In view of this, the purpose of the present invention is to provide a grid-based parallel, distributed method for recognizing faces, which is an improvement to the line segment-based face recognition method proposed by above-mentioned Olivier de Vel and Stefan Aeherhard, it It uses the powerful computing power and storage capacity of the grid, and through the mutual cooperation of each node in the grid, it better solves the vast and heavy computing work in the process of face recognition on the face database with a large amount of data. In order to meet the requirements of high-volume and massive storage, the high-accuracy face image recognition algorithm and the technical means of increasing resource consumption are used to solve the problems of face image contour acquisition and sensitivity to changes in light intensity, and realize high-precision face image recognition. Face Image Recognition

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
  • Parallel and distributing type identifying human face based on net
  • Parallel and distributing type identifying human face based on net
  • Parallel and distributing type identifying human face based on net

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0072] As we all know, the amount of calculation involved in face image recognition is very huge. As a grid-based parallel and distributed face recognition method, the present invention deploys the calculation and operation of face recognition processing on a grid platform. Each calculation node in the grid performs parallel and distributed operation processing of face recognition to reduce the time of face recognition; at the same time, more straight lines can be selected to improve the accuracy of face recognition.

[0073] see figure 2 , introduce the concrete operation steps of the inventive method:

[0074] Step (1): Configure the grid and establish a configurable computing node pool - first configure the grid, establish the connection between the managemen...

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

This invention relates to a parallel and distributed man-face identifying method based on network, which applies an improved man-face identifying method based on line sections to allocate the computing and operation on the network, utilizes the strong computation and storage ability of the nodes in the network and their corporation to carry out parallel and distributed identification operation to increase the identifying speed of man-faces. The method includes the following steps: configuring network to set up an adjustable node computation tank, picking up man-face images in a video flow.

Description

technical field [0001] The present invention relates to a technology for intelligent identification by comprehensively utilizing two computer application technologies, to be precise, it relates to a grid-based parallel and distributed face recognition method, which belongs to the comprehensive application of multimedia pattern recognition and grid computing technology field. Background technique [0002] Grid is a distributed computing technology that uses the network to gather computers and other network element devices in the network together, share resources in the network, and improve computing power. At present, there is no unified definition of the grid. Sun believes that the grid is a system that provides a single point of login to powerful distributed resources. IBM believes that grid computing is a technology that uses the Internet to connect processors in large-scale virtual systems to realize the desire to utilize shared resources. [0003] The research of grid ...

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): G06K9/00
Inventor 明安龙马华东张海旸
Owner BEIJING UNIV OF POSTS & TELECOMM
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