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

A face recognition attendance checking method and device

A technology of face recognition and face recognition, which is applied in the field of face recognition attendance methods and devices, can solve problems such as reducing system operating efficiency, wasting system resources, and wasting server system resources, so as to avoid analysis and detection, avoid resources, and improve The effect of recognition efficiency

Pending Publication Date: 2019-05-10
GUANGDONG ESHORE TECH
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, most of the collection devices for face recognition are cooperative, and each captured picture needs to be continuously analyzed and identified, which greatly wastes system resources, and unnecessary analysis and detection reduces the processing efficiency of the server
There are mainly the following defects: (1) Most of the face recognition for attendance is cooperative, and liveness detection is required, such as opening the mouth or turning the head left and right to ensure that the recognition is a living person. This series of operations will waste a certain amount of time. Therefore, it cannot achieve high efficiency in the true sense; (2) The server continuously analyzes the faces captured by the acquisition device. The recognition operation wastes the system resources of the server and greatly reduces the operating efficiency of the system; (3) based on the attendance method of face recognition, the ultra-large-scale training data improves the accuracy of face recognition, but in the actual application of the recognition speed and Efficiency remains a big challenge

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 attendance checking method and device
  • A face recognition attendance checking method and device
  • A face recognition attendance checking method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Such as Figure 6 Shown, also comprise before step S1 S00) the step of setting up attendance face information database, as figure 2 As shown, said S00) specifically includes steps:

[0067] S001. Multi-angle collection of face pictures: sequentially collect multi-angle face pictures of each person waiting for attendance;

[0068] S002. Picture quality judgment: judge whether the face quality in each face picture of the personnel to be checked reaches the requirement of judgment standard, if so, then save this picture, then enter step S003, otherwise delete this picture; Described judgment standard includes following one One or more types: whether the resolution exceeds the set value, whether the definition exceeds the set value, whether the Euler angle is greater than the set value; the size of the image resolution determines the amount of facial feature information, and the higher the resolution, the detected The more face information, but the more time-consuming; f...

Embodiment 2

[0073] Described S1) multi-angle collection face picture step, specifically:

[0074] By being on the same plane, the height H is 1.7≤H≤2.5 meters, the deviation is not more than 0.6 meters, the angle between the movement horizontal direction of the personnel to be checked and the collection is not more than 60 degrees, and the relative angle θ is 120°≤θ≤180°, The face pictures of each person to be checked are sequentially collected from multiple angles at a distance L of 1≤L≤5 meters from the person to be checked.

[0075] Specifically, the collection and deployment of multi-angle collection of face pictures includes: the location of the collection device, the number of devices n (n ≥ 2), the direction of the device, the distance between the device and the moving target, etc. The location of the device is divided into the height of the device , angle, relative position of n devices, etc. The deployment of equipment takes the number of equipment n=3 as an example. The locatio...

Embodiment 3

[0078] Said S4 specifically includes the following steps: as Figure 5 as shown,

[0079] S41. Feature loading: respectively load the face features from multiple angles and the face features in the attendance face information database into the memory;

[0080] Specifically, according to the frame rate of the video, a series of face pictures captured by the acquisition device can be recognized at 15 frames per second, and the interval is set to 60ms. People within this time interval can be considered as the same person, and the selection quality is better. Extract facial features from a series of pictures with faces centered, and load these features into memory.

[0081] S42. Feature comparison: the face features under multiple angles are compared with the data in the attendance face information database in memory;

[0082] S43. Judging the similarity: judging whether the facial features and similarity at any angle reach the threshold, if so, go to step S5; otherwise, output ...

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 a face recognition method and device. The method comprises the steps of collecting a face image from multiple angles; respectively detecting a human face in the human face image by using a deep convolutional neural network method; carrying out face registration on the face images at multiple angles by using an affine transformation method; carrying out alignment, extracting face features through rapid analysis, the face features at multiple angles are compared with data in an attendance face information database, whether the face features are personnel in a to-be-attendance face information base or not is judged, system resources are avoided, unnecessary analysis and detection are avoided, non-cooperative face recognition is rapidly carried out, and the recognitionefficiency is improved.

Description

technical field [0001] The invention relates to the field of work attendance, in particular to a face recognition work attendance method and device. Background technique [0002] With the advent of the era of "face scanning", face recognition technology has continuously achieved new research results in the field of artificial intelligence. The recognition method based on the deep convolutional neural network model has improved the accuracy of face recognition. Now, more and more artificial intelligence research results have entered people's daily life and work. Face recognition attendance is an application of face recognition technology. Compared with traditional induction punch cards and fingerprint attendance, face recognition attendance is based on The irreplaceable feature of the human face is intuitive and friendly, and at the same time, it can eliminate the phenomenon of punching cards. [0003] Face recognition technology is a specific application in the field of com...

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): G06K9/00G06K9/62G07C1/10
Inventor 刘华好王立强宋建斌张青吴武勋吴冬冬邹东杰
Owner GUANGDONG ESHORE TECH
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