An Attendance System Based on Gesture Recognition
A gesture and recognition module technology, applied in the field of attendance system based on gesture recognition, can solve problems such as complex deep learning operations
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0043] An attendance system based on gesture recognition, the attendance system includes:
[0044] A monitoring module, the monitoring module is composed of one or more cameras and is used to identify employees in the area to be monitored;
[0045] Gesture recognition module, described gesture recognition module is used for carrying out gesture recognition to employee group;
[0046] A determination module, the determination module is used to perform gesture recognition according to different gestures of individual employees, and determine the personal information of the corresponding employee on duty.
[0047] The personal information includes employee number, employee name, department, attendance time and so on.
Embodiment 2
[0049] On the basis of the attendance system described in embodiment 1, the attendance system also includes:
[0050] Face recognition module, the face recognition module is different from the conventional face recognition that needs to be close to the terminal, but based on face recognition under long-distance monitoring, which is suitable for centralized attendance attendance of large-scale employees without sequentially face recognition;
[0051] A movement tracking module, when the determination module cannot identify an employee with a certain posture, the movement tracking module will continue to track the employee for a first predetermined period of time, and continue to determine the posture by the determination module;
[0052] When the employee with a certain gesture still cannot be identified within the first predetermined period of time, start the face recognition module to recognize the face of the employee;
[0053] When the face recognition module cannot identi...
Embodiment 3
[0058] On the basis of the attendance system described in embodiment 2, the gesture recognition module is specifically:
[0059] The gesture recognition model is set up, and the gesture recognition model adopts a deep convolutional neural network structure, including an input layer, a bidirectional long-short-term memory network BiLSTM layer, a convolution layer, a pooling layer, a locally connected layer, and a fully connected layer. The convolution layer adopts a convolution kernel of 7*7 and 16 filters; the pooling window size of the pooling layer is 3*3, and the number of channels is 32; the local connection layer adopts 32 filters, 32 Channel, 3*3 convolution kernel; the input of the fully connected layer comes from the output of the local connection layer; the pooling method of the pooling layer is as follows:
[0060] x e =f(u e +φ(u e ))
[0061]
[0062] where x e Indicates the output of the current layer, u e Represents the input of the activation function, ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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