A high-precision portrait recognition method and system for security monitoring

A technology of portrait recognition and security monitoring, which is applied in the field of portrait recognition, can solve the problems of poor recognition accuracy and incapable of real-time analysis of portrait information, so as to improve efficiency, improve accuracy, and overcome poor accuracy

Active Publication Date: 2021-12-07
AYLA NETWORKS (SHENZHEN) LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a high-precision portrait recognition method and system for security monitoring. Technical issues with poor precision

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 high-precision portrait recognition method and system for security monitoring
  • A high-precision portrait recognition method and system for security monitoring
  • A high-precision portrait recognition method and system for security monitoring

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] see figure 1 As shown, the present invention is a high-precision portrait recognition method for security monitoring, and the specific steps include:

[0049] S1: Collect face image sets and perform preprocessing operations to obtain face processing sets; specific steps include:

[0050] Obtaining the original image in the face image set, and cutting the original image according to a preset cutting size to obtain a cut image;

[0051] Perform grayscale correction on the cropped image to obtain the first processed image, and perform noise filtering on the first processed image to obtain the second processed image; wherein, the grayscale correction is realized based on the existing image grayscale algorithm, such as the one disclosed in the publication number CN105208362A Method; Noise filtering is realized based on existing image noise algorithms, such as non-local mean denoising algorithm;

[0052] Combining several second processed images to obtain a face processing ...

Embodiment 2

[0082] A high-precision portrait recognition system for security monitoring, including a collection preprocessing module, a feature extraction module, an analysis and calculation module, and a matching module; the collection and preprocessing module is used to collect face image sets and perform preprocessing operations to obtain face processing sets ; The feature extraction module is used to perform feature extraction on the face processing set to obtain the face extraction set, which contains the contour data and feature data of the face; the analysis and calculation module is used to analyze and calculate the face extraction set to obtain the face profile value and face value, analyze the face profile value and face value to obtain the analysis set; the matching module is used to match the analysis set with the pre-stored analysis data in the database to obtain the analysis result;

[0083] Compared with the existing technical solutions, in the embodiment of the present inve...

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 high-precision portrait recognition method for security monitoring. By collecting a face image set and performing a preprocessing operation, a face processing set is obtained; by performing feature extraction on the face processing set, a face extraction set is obtained. The face extraction set contains the contour data and feature data of the face; through the analysis and calculation of the face extraction set, the face contour value and face characteristic value are obtained, and the analysis set is obtained by analyzing the face contour value and face characteristic value; the analysis set is combined with The analysis data pre-stored in the database are matched to obtain the analysis results; the invention also discloses a high-precision portrait recognition system for security monitoring; various aspects disclosed in the invention solve the problem that the existing solutions cannot perform real-time analysis on the collected portrait information And carry out secondary processing verification to overcome the influence of the external environment on the recognition, resulting in the technical problem of poor recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of portrait recognition, in particular to a high-precision portrait recognition method and system for security monitoring. Background technique [0002] The security monitoring system uses optical fiber, coaxial cable or microwave to transmit video signals in its closed loop, and constitutes an independent and complete system from camera to image display and recording; face recognition is based on human facial feature information for identification A biometric identification technology for recognition; traditional face recognition technology is mainly based on visible light image face recognition, but this method has insurmountable defects, especially when the ambient light changes, the recognition effect will drop sharply, which cannot meet actual system needs. [0003] The defects of the existing high-precision portrait recognition methods for security monitoring include: the inability to analyze the coll...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/46
CPCG06V40/172G06V40/171G06V10/44
Inventor 唐平麟宋克强
Owner AYLA NETWORKS (SHENZHEN) LTD
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