Human face recognition method and system based on feature comparison of key regions

A key area and face recognition technology, applied in the field of face recognition, can solve problems such as insufficient understanding of meaning, immature research, and reduction of the calculation amount of recognition methods

Active Publication Date: 2018-09-14
光控特斯联(上海)信息科技有限公司
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the above method is not mature enough for the research on the key areas in the local feature analysis, or the significance of the key area feature analysis for improving the recogni

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
  • Human face recognition method and system based on feature comparison of key regions
  • Human face recognition method and system based on feature comparison of key regions
  • Human face recognition method and system based on feature comparison of key regions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0106] The present invention will be further described below in conjunction with the accompanying drawings.

[0107] A face recognition method based on key region feature comparison, comprising the steps of:

[0108] (1) Face image acquisition:

[0109] The image acquisition device collects color images in real time, according to the RGB (red, green and blue) color mode, that is, the color of each pixel is represented by three components of red, green and blue, and grayscales the color image, and the value range is 0 to 255 The gray value or brightness value; 0 is the darkest for black, 255 is the brightest for white;

[0110] Described grayscale processing specifically comprises: take the upper left corner of the color image as the zero coordinate, the upper boundary of the color image as the x-axis, and the left boundary of the color image as the y-axis; x, y), G(x, y), B(x, y) represent the red, green and blue components of the pixel, and use q(x, y) to represent the gray...

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 belongs to the technical field of human face recognition, and specifically relates to a human face recognition method and system based on feature comparison of key regions with improvedrecognition speed and enhanced precision. The human face recognition method based on feature comparison of key regions comprises a step of human face image acquisition, a step of human face calibration, a step of classification of human face features via a classifier, a step of human face feature extraction in key areas, a step of comparing human face features of key areas to complete human face recognition, and a step of conducting feature analysis and in-depth learning. The method comprises human face feature extraction, feature calibration, and error rate-based judgment and classification so as to attain an aim of human face recognition; an aim of accuracy improvement can be attained via multi-mode fusion.

Description

technical field [0001] The invention belongs to the technical field of face recognition, and in particular relates to a face recognition method and system based on key region feature comparison with faster recognition speed and higher accuracy. Background technique [0002] Face recognition occurs in daily life all the time, and it refers to the process of identity verification based on the facial feature information of a person. The human brain can easily judge the identity of the person by observing the face, but it is not an easy task for the computer. Generally speaking, automatic face recognition refers to the use of image acquisition equipment to first collect static images or dynamic video streams containing human faces, and then automatically detect and track human faces in the images or video streams through computer algorithms, and then to detect or track human faces. The process of extracting and recognizing facial feature information of human faces. The researc...

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): G06K9/00G06K9/62
CPCG06V40/165G06V40/171G06V40/172G06F18/22
Inventor 刘丰
Owner 光控特斯联(上海)信息科技有限公司
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