Adaptive local face recognition method and system for security field

A face recognition, self-adaptive technology, applied in character and pattern recognition, computer parts, instruments, etc., to achieve the effect of improving accuracy and efficiency

Pending Publication Date: 2021-12-31
的卢技术有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the current face recognition training is based on complete face extraction features, so it is difficult to accurately recognize faces wearing masks. For these situations, an algorithm is required to adaptively use visible features for face 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
  • Adaptive local face recognition method and system for security field

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] A method for self-adaptive partial face recognition in the field of security, comprising the following steps:

[0026] (1) The security camera acquires images captured in real time;

[0027] (2) The image acquisition module judges the quality of the continuous multi-frame images collected in the step (1), and preprocesses the first three pictures with the best quality; the processing result is output to the local face detection module;

[0028] (3) The partial face detection module uses the partial face detection model trained by deep learning to perform face detection, and detects the bounding boxes of visible partial faces and the corresponding face area categories; the processing results are output to post-processing of face detection module;

[0029] (4) The post-processing module of face detection carries out 0-filling operation to the short side of each face area identified, and fills the partial image into a square; the processing result is output to the face re...

Embodiment 2

[0032] An adaptive partial face recognition system used in the security field, including the following modules:

[0033] Image acquisition module: the security camera acquires images captured in real time, judges the quality of the captured continuous frame images, and preprocesses the first three images with the best quality;

[0034] Partial face detection module: The input of this module is the output after image acquisition and preprocessing, that is, several photos; this module uses the partial face detection model trained by deep learning for face detection, and detects the visible part of the face The bounding box and the corresponding face area category;

[0035] Face detection post-processing module: the input of this module is the face area returned after passing through the partial face detection module, and each recognized face area is filled with 0 on the short side to fill the partial image into a square;

[0036] Face recognition module: The input of this modul...

Embodiment 3

[0038] A computer storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned self-adaptive partial face recognition method used in the security field is realized.

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 an adaptive local face recognition method and system used in the field of security protection. The method comprises the steps: firstly determining the region type of a detected face region, and then carrying out the feature similarity calculation of the same region type. The system comprises an image acquisition module, a local face detection module, a face detection post-processing module and a face recognition module. For the problem of face posture diversity in the field of security protection, face recognition can be realized under the condition that a front-view camera is not needed. According to the method, a large number of samples which are locally visible and worn with masks or other shelters are used in model training, so that the situation that the faces with worn masks cannot be recognized in the gates of airports and stations can be greatly improved, and the accuracy and efficiency of face recognition in the security field are greatly improved.

Description

technical field [0001] The invention relates to security, in particular to an adaptive partial face recognition method and system for the field of security. Background technique [0002] In recent years, face recognition has penetrated into all aspects of life, which greatly facilitates our life. In addition to the convenience, the accuracy and safety of face recognition are increasingly tested. In the actual security field, such as the airport station with a large traffic flow, the face recognition system may not be able to capture a complete picture. In this case, the existing algorithm may fail to recognize the face, so it is very useful. It is necessary to design a system that can recognize partial faces. [0003] The effective features of a face picture mainly include the contour features of the face, the main facial features extracted from the eyes, nose, mouth, etc., and the combination of these local features. The remaining features do not have an important impact ...

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 闫守志
Owner 的卢技术有限公司
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