A method for identifying a face according to an image

An image recognition and image technology, which is applied in the field of face recognition based on images, can solve the problems of inconvenient data query for prisoners, feature extraction of head portraits of difficult persons, and increase the difficulty of arresting prisoners, etc., to achieve convenient query and confirmation, rapid analysis, and convenient The effect of data query

Pending Publication Date: 2019-04-05
广东腾晟信息科技有限公司
View PDF11 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In the process of integrating the criminal person's video information, it is necessary to take a screenshot of the criminal person's image, and then perform feature analysis based on the person image, retrieve and analyze the information in the person image, and compare it with the person information in the database, so as to facilitate the query of criminals Most of the existing methods for character identification use personnel observation or character image analysis, but the resolution of the picture information in the surveillance video is low, and it is difficult to extract the features of the head portrait of the person in the surveillance, which is not convenient for the prisoner Inquiry of the data, increasing the difficulty of arresting criminals

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 method for identifying a face according to an image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] A method for recognizing a face from an image, comprising the following steps:

[0035] 1) Selection of the avatar of the original character:

[0036] In the surveillance video, the avatar of the target person in the video is intercepted, and the image characteristics of multiple screenshots are analyzed for backup.

[0037] 2), conversion of low-resolution pictures and high-resolution pictures:

[0038] Use the resolution adjustment software RAISR to combine multiple low-resolution images with the same features into a high-resolution image for backup;

[0039] 3) Analysis of the original image:

[0040] The integrated high-resolution image is imported into the analysis equipment for image scanning and analysis, and the analyzed avatar data is integrated, and 3D modeling is carried out through the modeling software. The 3D modeling software is Maya modeling software, which is spare.

[0041] 4) Extraction and analysis of avatar features:

[0042] Extract the feature...

Embodiment 2

[0054] A method for recognizing a face from an image, comprising the following steps:

[0055] 1) Selection of the avatar of the original character:

[0056] In the surveillance video, the avatar of the target person in the video is intercepted, and the image characteristics of multiple screenshots are analyzed for backup.

[0057] 2), conversion of low-resolution pictures and high-resolution pictures:

[0058] Use the resolution adjustment software RAISR to combine multiple low-resolution images with the same features into a high-resolution image for backup;

[0059] 3) Analysis of the original image:

[0060]The integrated high-resolution image is imported into the analysis equipment for image scanning and analysis, and the analyzed avatar data is integrated, and 3D modeling is carried out through the modeling software. The 3D modeling software is Maya modeling software, which is spare.

[0061] 4) Extraction and analysis of avatar features:

[0062] Extract the features...

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 relates to the technical field of computer vision. The invention particularly relates to a method for identifying a face according to an image. The method comprises the following steps of head portrait selection of an original person, conversion of a low-resolution picture and a high-resolution picture, analysis of the original image, extraction and analysis of head portrait characteristics, data transmission of the head portrait characteristics, screening of comparison images, analysis of the comparison images, comparison of the characteristics of the original image and the characteristics of the comparison images and confirmation of the head portraits of the person. According to the invention, analysis modeling is carried out on face features in a figure video; converting the low-resolution picture into a high-resolution picture; Characteristics in the comparison image are integrated, data comparison is conducted on the character characteristics and the characteristicsin the comparison image, identity information of the character is conveniently identified, the advantages that information of criminal offenders is conveniently inquired and confirmed, data inquiry ofthe criminal offenders is facilitated are achieved, the identity information inquiry efficiency is improved, and the accuracy is higher.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for recognizing human faces based on images. Background technique [0002] In the process of integrating the criminal person's video information, it is necessary to take a screenshot of the criminal person's image, and then perform feature analysis based on the person image, retrieve and analyze the information in the person image, and compare it with the person information in the database, so as to facilitate the query of criminals Most of the existing methods for character identification use personnel observation or character image analysis, but the resolution of the picture information in the surveillance video is low, and it is difficult to extract the features of the head portrait of the person in the surveillance, which is not convenient for the prisoner Inquiry of the data, which increases the difficulty of arresting criminals. Contents of the invention ...

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): G06K9/00G06T3/40
CPCG06T3/4053G06V40/161G06V40/168
Inventor 陈华陈乐瑶
Owner 广东腾晟信息科技有限公司
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