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

A Face Recognition Method

A face recognition and face technology, applied in the field of face recognition, can solve the problems of low recognition accuracy and affect recognition efficiency, and achieve the effect of high recognition accuracy, high picture quality, and improved efficiency.

Inactive Publication Date: 2019-01-04
力当高(上海)智能科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the prior art, due to the problem of the shooting angle, when the collected image is a side face, since all facial information cannot be collected, the recognition method in the prior art will cause more inconvenience during recognition, thus affecting the Subsequent recognition efficiency leads to low 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
  • A Face Recognition Method
  • A Face Recognition Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] A face recognition method, specifically comprising the following steps:

[0025] Step 1. Facial image processing: collect the frontal facial images of residents, and then optimize and intercept the facial images. The height of the intercepted image is the distance from the brow center to the chin of the face in the picture, and the width is between the ears. The distance, at this time the image height is set to x 1 , the image width is set to y 1 , register and back up the obtained image;

[0026] Step 2. Building the face database: Segment the image obtained in step 1, that is, divide an image into the right face image along the longitudinal middle, and the height of the right face image is x 1 , with a width of y 1 / 2 image, and then mirror the right face image along the split, so that the right face image specification is restored to a height of x 1 , with a width of y 1 , and then save the above-mentioned right face image and the information of the residents in...

Embodiment 2

[0033] A face recognition method, specifically comprising the following steps:

[0034] Step 1. Facial image processing: collect the frontal facial images of residents, and then optimize and intercept the facial images. The height of the intercepted image is the distance from the brow center to the chin of the face in the picture, and the width is between the ears. The distance, at this time the image height is set to x 1 , the image width is set to y 1 , register and back up the obtained image;

[0035] Step 2. Building the face database: Segment the image obtained in step 1, that is, divide an image into the right face image along the longitudinal middle, and the height of the right face image is x 1 , with a width of y 1 / 2 image, and then mirror the right face image along the split, so that the right face image specification is restored to a height of x 1 , with a width of y 1 , and then save the above-mentioned right face image and the information of the residents in...

Embodiment 3

[0042] The optimization in the step 1 is image definition adjustment and brightness adjustment, so that the picture quality of the template image is higher, which facilitates subsequent identification;

[0043] The optimization in step 3 is image definition adjustment and brightness adjustment, so that the picture quality of the image to be recognized is higher, and the situation of affecting the recognition accuracy rate caused by poor picture quality is avoided;

[0044] In said step 6, when the final contrast image is compared with the image in the face database, a big data processing center is used for comparison. Because the big data processing center has extremely high bandwidth and computing speed, it can effectively improve the efficiency of image recognition and reduce time consumed.

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 method for recognizing human face. The method includes the following steps: 1, processing the face image, wherein a front face image is collected, and the face image is optimized and cut out, the image height is the distance between the brow center of the human face and the chin, and the width is the distance between the ears. At this time, the image height is set to x1,and the image width is set to y1. The obtained image is registered and backed up. As the image is adjusted in the transverse length and the longitudinal length according to the shooting angle, the image is then mirrored, thereby converting the side face image into a symmetrical whole face image, therefore, the invention can be compared with two symmetrical images formed by the left and right facesof the resident image in the subsequent picture recognition, and the image to be recognized can be processed and recognized effectively under the condition that all the face information cannot be collected, so that the recognition accuracy is high.

Description

technical field [0001] The invention relates to the technical fields of image processing and pattern recognition, in particular to a face recognition method. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. A series of related technologies that use a video camera or camera to collect images or video streams containing human faces, automatically detect and track human faces in the images, and then perform facial recognition on the detected faces, usually also called portrait recognition and facial recognition. . [0003] In the prior art, due to the problem of the shooting angle, when the collected image is a side face, since all facial information cannot be collected, the recognition method in the prior art will cause more inconvenience during recognition, thus affecting the Subsequent recognition efficiency leads to low recognition accuracy. [0004] Therefore, it is necessary to invent...

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): G06K9/00G06K9/34G06F16/53
CPCG06V40/165G06V10/267
Inventor 王海洁曹真龙曹龙飞陈琳胡於干魏云燕
Owner 力当高(上海)智能科技有限公司
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