Unlock instant, AI-driven research and patent intelligence for your innovation.

Face recognition device and method based on multi-angle video

A face recognition, multi-angle technology, applied in the field of face recognition devices, can solve problems such as the impact of accuracy, and achieve the effect of improving robustness and recognition rate

Active Publication Date: 2020-11-06
SUZHOU UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, existing face recognition systems usually use a single image for face identity recognition, which makes the collected images susceptible to interference from factors such as illumination, recognition environment, face pose, and shooting angle. When using the face recognition algorithm to determine the identity of the face, the accuracy will be affected to a certain extent

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
  • Face recognition device and method based on multi-angle video
  • Face recognition device and method based on multi-angle video
  • Face recognition device and method based on multi-angle video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Refer to attached figure 1, the face recognition device based on multi-angle video in the present embodiment, it comprises a face recognition processing control unit, a recognition channel (not shown in the accompanying drawings), installed on the recognition channel and connected with the face recognition processing control unit At least three cameras connected by signals, at least three cameras including the first camera 1 arranged directly above the recognition channel and used to collect the user's front face features, and the first camera 1 arranged on the left side of the recognition channel and used to collect the user's left face features At least one second camera 2, at least one third camera 3 arranged on the right side of the recognition channel and used to collect the features of the user's right face.

[0039] In a more preferred embodiment, a supplementary light (not shown in the drawings) for providing fixed illumination for the camera is installed on the...

Embodiment 2

[0054] Refer to attached Figure 4 The difference between this embodiment and Embodiment 1 is that in step b5 of the face recognition method using a multi-angle video-based face recognition device, the recognition strategy is: the candidate sets whose similarity is greater than the preset threshold The candidate objects are merged into a new candidate set, and the number of the same candidate objects in the new candidate set is accumulated. If the proportion of the number of the same candidate objects to all candidate objects is greater than the preset threshold, then The candidate object corresponding to the current threshold is taken as the final recognition result; otherwise, the user is judged as a stranger, that is, it does not belong to a registered user.

Embodiment 3

[0056] Refer to attached Figure 5 , the difference between this embodiment and Embodiment 1 is that in step b5 of the face recognition method using a multi-angle video-based face recognition device, the recognition strategy is: first select the candidate with the largest similarity in each candidate set Objects, and then form them into a new candidate set, and count the number of the same candidate object in the new candidate set, if the maximum value of the obtained value is greater than or equal to 3, then the candidate object corresponding to the value is used as the final Recognition result; if the maximum value obtained is less than 3 and greater than or equal to 2, and the second maximum value is not 2, the candidate object corresponding to the value 2 will be used as the final recognition result; if the maximum value obtained is is less than 3 and greater than or equal to 2, and the second largest value is also 2, then compare the sum of their similarities, and take th...

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 face recognition device and method based on multi-angle video. The multi-angle video-based face recognition device comprises a face recognition processing control unit, a recognition channel, a face recognition channel installed on the recognition channel, and a face recognition device. At least three cameras connected to the processing control unit with signals, the at least three cameras include a first camera arranged directly above the identification channel and used to collect the features of the user's face, a first camera arranged on the left side of the identification channel and used to collect the user's left side At least one second camera for facial features, and at least one third camera for collecting the facial features on the right side of the user, arranged on the right side of the identification channel. The face recognition method using the above-mentioned multi-angle video-based face recognition device includes face registration, face detection and recognition.

Description

technical field [0001] The invention relates to a face recognition device and method based on multi-angle video. Background technique [0002] With the development of biometric technology, more and more face recognition technology has entered people's lives. Face recognition attendance technology has the advantages of non-contact, intuitive, friendly, and strong applicability. At present, face recognition technology has broken through the influence of day and night light, and can achieve rapid recognition in a natural state. Nowadays, with the continuous maturity of technology and the reduction of cost, face attendance has gradually shown the trend of replacing fingerprint attendance. In terms of biometrics, the application of face recognition technology has gradually exceeded the field of security technology. [0003] The face recognition system mainly includes four modules: face detection, face alignment, feature extraction and identity recognition. Face detection, fir...

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): G06K9/00
CPCG06V40/166G06V40/168
Inventor 刘光富赵雷
Owner SUZHOU UNIV